author
stringlengths
2
29
cardData
null
citation
stringlengths
0
9.58k
description
stringlengths
0
5.93k
disabled
bool
1 class
downloads
float64
1
1M
gated
bool
2 classes
id
stringlengths
2
108
lastModified
stringlengths
24
24
paperswithcode_id
stringlengths
2
45
private
bool
2 classes
sha
stringlengths
40
40
siblings
list
tags
list
readme_url
stringlengths
57
163
readme
stringlengths
0
977k
naver-clova-ix
null
null
null
false
1,110
false
naver-clova-ix/cord-v1
2022-07-14T14:08:12.000Z
null
false
64fe41966657fbf60c1443a84143a2081dbd50a6
[]
[ "license:cc-by-4.0" ]
https://huggingface.co/datasets/naver-clova-ix/cord-v1/resolve/main/README.md
--- license: cc-by-4.0 ---
felipe3dartist
null
null
null
false
1
false
felipe3dartist/portrait_generator_v001_initImages
2022-07-14T14:26:47.000Z
null
false
a45a9eab6fc10b4e2e100e01847c2e4a3f73e8db
[]
[ "license:cc-by-nc-4.0" ]
https://huggingface.co/datasets/felipe3dartist/portrait_generator_v001_initImages/resolve/main/README.md
--- license: cc-by-nc-4.0 ---
Ciara
null
null
null
false
1
false
Ciara/nlsn
2022-07-14T14:56:07.000Z
null
false
fa83741c5357d84b6f14110210b0c3a990d91f6b
[]
[ "license:afl-3.0" ]
https://huggingface.co/datasets/Ciara/nlsn/resolve/main/README.md
--- license: afl-3.0 ---
14-07-22
null
Anonymous submission
Anonymous submission
false
1
false
14-07-22/wikimedqa
2022-07-15T12:56:32.000Z
null
false
5e19492424be123d8a8a281105ec5e3094841a29
[]
[ "license:apache-2.0" ]
https://huggingface.co/datasets/14-07-22/wikimedqa/resolve/main/README.md
--- license: apache-2.0 ---
autoevaluate
null
null
null
false
1
false
autoevaluate/autoeval-staging-eval-project-kmfoda__booksum-79c1c0d8-10905465
2022-07-15T20:08:50.000Z
null
false
c487794585c57af63b407e88cb4ff68ff49a84e5
[]
[ "type:predictions", "tags:autotrain", "tags:evaluation", "datasets:kmfoda/booksum" ]
https://huggingface.co/datasets/autoevaluate/autoeval-staging-eval-project-kmfoda__booksum-79c1c0d8-10905465/resolve/main/README.md
--- type: predictions tags: - autotrain - evaluation datasets: - kmfoda/booksum eval_info: task: summarization model: pszemraj/pegasus-large-summary-explain metrics: ['bleu', 'perplexity'] dataset_name: kmfoda/booksum dataset_config: kmfoda--booksum dataset_split: test col_mapping: text: chapter target: summary_text --- # Dataset Card for AutoTrain Evaluator This repository contains model predictions generated by [AutoTrain](https://huggingface.co/autotrain) for the following task and dataset: * Task: Summarization * Model: pszemraj/pegasus-large-summary-explain * Dataset: kmfoda/booksum * Config: kmfoda--booksum * Split: test To run new evaluation jobs, visit Hugging Face's [automatic model evaluator](https://huggingface.co/spaces/autoevaluate/model-evaluator). ## Contributions Thanks to [@pszemraj](https://huggingface.co/pszemraj) for evaluating this model.
demelin
null
@article{Srivastava2022BeyondTI, title={Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models}, author={Aarohi Srivastava and Abhinav Rastogi and Abhishek B Rao and Abu Awal Md Shoeb and Abubakar Abid and Adam Fisch and Adam R. Brown and Adam Santoro and Aditya Gupta and Adri{\`a} Garriga-Alonso and Agnieszka Kluska and Aitor Lewkowycz and Akshat Agarwal and Alethea Power and Alex Ray and Alex Warstadt and Alexander W. Kocurek and Ali Safaya and Ali Tazarv and Alice Xiang and Alicia Parrish and Allen Nie and Aman Hussain and Amanda Askell and Amanda Dsouza and Ameet Annasaheb Rahane and Anantharaman S. Iyer and Anders Johan Andreassen and Andrea Santilli and Andreas Stuhlmuller and Andrew M. Dai and Andrew D. La and Andrew Kyle Lampinen and Andy Zou and Angela Jiang and Angelica Chen and Anh Vuong and Animesh Gupta and Anna Gottardi and Antonio Norelli and Anu Venkatesh and Arash Gholamidavoodi and Arfa Tabassum and Arul Menezes and Arun Kirubarajan and Asher Mullokandov and Ashish Sabharwal and Austin Herrick and Avia Efrat and Aykut Erdem and Ayla Karakacs and Bridget R. Roberts and Bao Sheng Loe and Barret Zoph and Bartlomiej Bojanowski and Batuhan Ozyurt and Behnam Hedayatnia and Behnam Neyshabur and Benjamin Inden and Benno Stein and Berk Ekmekci and Bill Yuchen Lin and Blake Stephen Howald and Cameron Diao and Cameron Dour and Catherine Stinson and Cedrick Argueta and C'esar Ferri Ram'irez and Chandan Singh and Charles Rathkopf and Chenlin Meng and Chitta Baral and Chiyu Wu and Chris Callison-Burch and Chris Waites and Christian Voigt and Christopher D. Manning and Christopher Potts and Cindy Tatiana Ramirez and Clara Rivera and Clemencia Siro and Colin Raffel and Courtney Ashcraft and Cristina Garbacea and Damien Sileo and Daniel H Garrette and Dan Hendrycks and Dan Kilman and Dan Roth and Daniel Freeman and Daniel Khashabi and Daniel Levy and Daniel Gonz'alez and Danny Hernandez and Danqi Chen and Daphne Ippolito and Dar Gilboa and David Dohan and D. Drakard and David Jurgens and Debajyoti Datta and Deep Ganguli and Denis Emelin and Denis Kleyko and Deniz Yuret and Derek Chen and Derek Tam and Dieuwke Hupkes and Diganta Misra and Dilyar Buzan and Dimitri Coelho Mollo and Diyi Yang and Dong-Ho Lee and Ekaterina Shutova and Ekin Dogus Cubuk and Elad Segal and Eleanor Hagerman and Elizabeth Barnes and Elizabeth P. Donoway and Ellie Pavlick and Emanuele Rodol{\`a} and Emma FC Lam and Eric Chu and Eric Tang and Erkut Erdem and Ernie Chang and Ethan A. Chi and Ethan Dyer and Ethan Jerzak and Ethan Kim and Eunice Engefu Manyasi and Evgenii Zheltonozhskii and Fan Xia and Fatemeh Siar and Fernando Mart'inez-Plumed and Francesca Happ'e and François Chollet and Frieda Rong and Gaurav Mishra and Genta Indra Winata and Gerard de Melo and Germ{\'a}n Kruszewski and Giambattista Parascandolo and Giorgio Mariani and Gloria Wang and Gonzalo Jaimovitch-L'opez and Gregor Betz and Guy Gur-Ari and Hana Galijasevic and Han Sol Kim and Hannah Rashkin and Hanna Hajishirzi and Harsh Mehta and Hayden Bogar and Henry Shevlin and Hinrich Sch{\"u}tze and Hiromu Yakura and Hongming Zhang and Hubert Wong and Ian Aik-Soon Ng and Isaac Noble and Jaap Jumelet and Jack Geissinger and John Kernion and Jacob Hilton and Jaehoon Lee and Jaime Fern{\'a}ndez Fisac and J. Brooker Simon and James Koppel and James Zheng and James Zou and Jan Koco'n and Jana Thompson and Jared Kaplan and Jarema Radom and Jascha Narain Sohl-Dickstein and Jason Phang and Jason Wei and Jason Yosinski and Jekaterina Novikova and Jelle Bosscher and Jenni Marsh and Jeremy Kim and Jeroen Taal and Jesse Engel and Jesujoba Oluwadara Alabi and Jiacheng Xu and Jiaming Song and Jillian Tang and Jane W Waweru and John Burden and John Miller and John U. Balis and Jonathan Berant and Jorg Frohberg and Jos Rozen and Jos{\'e} Hern{\'a}ndez-Orallo and Joseph Boudeman and Joseph Jones and Joshua B. Tenenbaum and Joshua S. Rule and Joyce Chua and Kamil Kanclerz and Karen Livescu and Karl Krauth and Karthik Gopalakrishnan and Katerina Ignatyeva and Katja Markert and Kaustubh D. Dhole and Kevin Gimpel and Kevin Ochieng’ Omondi and Kory Wallace Mathewson and Kristen Chiafullo and Ksenia Shkaruta and Kumar Shridhar and Kyle McDonell and Kyle Richardson and Laria Reynolds and Leo Gao and Li Zhang and Liam Dugan and Lianhui Qin and Lidia Contreras-Ochando and Louis-Philippe Morency and Luca Moschella and Luca Lam and Lucy Noble and Ludwig Schmidt and Luheng He and Luis Oliveros Col'on and Luke Metz and Lutfi Kerem cSenel and Maarten Bosma and Maarten Sap and Maartje ter Hoeve and Madotto Andrea and Maheen Saleem Farooqi and Manaal Faruqui and Mantas Mazeika and Marco Baturan and Marco Marelli and Marco Maru and M Quintana and Marie Tolkiehn and Mario Giulianelli and Martha Lewis and Martin Potthast and Matthew Leavitt and Matthias Hagen and M'aty'as Schubert and Medina Baitemirova and Melissa Arnaud and Melvin Andrew McElrath and Michael A. Yee and Michael Cohen and Mi Gu and Michael I. Ivanitskiy and Michael Starritt and Michael Strube and Michal Swkedrowski and Michele Bevilacqua and Michihiro Yasunaga and Mihir Kale and Mike Cain and Mimee Xu and Mirac Suzgun and Monica Tiwari and Mohit Bansal and Moin Aminnaseri and Mor Geva and Mozhdeh Gheini and T MukundVarma and Nanyun Peng and Nathan Chi and Nayeon Lee and Neta Gur-Ari Krakover and Nicholas Cameron and Nicholas S. Roberts and Nicholas Doiron and Nikita Nangia and Niklas Deckers and Niklas Muennighoff and Nitish Shirish Keskar and Niveditha Iyer and Noah Constant and Noah Fiedel and Nuan Wen and Oliver Zhang and Omar Agha and Omar Elbaghdadi and Omer Levy and Owain Evans and Pablo Antonio Moreno Casares and Parth Doshi and Pascale Fung and Paul Pu Liang and Paul Vicol and Pegah Alipoormolabashi and Peiyuan Liao and Percy Liang and Peter W. Chang and Peter Eckersley and Phu Mon Htut and Pi-Bei Hwang and P. Milkowski and Piyush S. Patil and Pouya Pezeshkpour and Priti Oli and Qiaozhu Mei and QING LYU and Qinlang Chen and Rabin Banjade and Rachel Etta Rudolph and Raefer Gabriel and Rahel Habacker and Ram'on Risco Delgado and Rapha{\"e}l Milli{\`e}re and Rhythm Garg and Richard Barnes and Rif A. Saurous and Riku Arakawa and Robbe Raymaekers and Robert Frank and Rohan Sikand and Roman Novak and Roman Sitelew and Ronan Le Bras and Rosanne Liu and Rowan Jacobs and Rui Zhang and Ruslan Salakhutdinov and Ryan Chi and Ryan Lee and Ryan Stovall and Ryan Teehan and Rylan Yang and Sahib J. Singh and Saif M. Mohammad and Sajant Anand and Sam Dillavou and Sam Shleifer and Sam Wiseman and Samuel Gruetter and Sam Bowman and Samuel S. Schoenholz and Sanghyun Han and Sanjeev Kwatra and Sarah A. Rous and Sarik Ghazarian and Sayan Ghosh and Sean Casey and Sebastian Bischoff and Sebastian Gehrmann and Sebastian Schuster and Sepideh Sadeghi and Shadi Sameh Hamdan and Sharon Zhou and Shashank Srivastava and Sherry Shi and Shikhar Singh and Shima Asaadi and Shixiang Shane Gu and Shubh Pachchigar and Shubham Toshniwal and Shyam Upadhyay and Shyamolima Debnath and Siamak Shakeri and Simon Thormeyer and Simone Melzi and Siva Reddy and Sneha Priscilla Makini and Soo-hwan Lee and Spencer Bradley Torene and Sriharsha Hatwar and Stanislas Dehaene and Stefan Divic and Stefano Ermon and Stella Rose Biderman and Stephanie C. Lin and Stephen Prasad and Steven T. Piantadosi and Stuart M. Shieber and Summer Misherghi and Svetlana Kiritchenko and Swaroop Mishra and Tal Linzen and Tal Schuster and Tao Li and Tao Yu and Tariq A. Ali and Tatsuo Hashimoto and Te-Lin Wu and Theo Desbordes and Theodore Rothschild and Thomas Phan and Tianle Wang and Tiberius Nkinyili and Timo Schick and T. N. Kornev and Timothy Telleen-Lawton and Titus Tunduny and Tobias Gerstenberg and Trenton Chang and Trishala Neeraj and Tushar Khot and Tyler O. Shultz and Uri Shaham and Vedant Misra and Vera Demberg and Victoria Nyamai and Vikas Raunak and Vinay V. Ramasesh and Vinay Uday Prabhu and Vishakh Padmakumar and Vivek Srikumar and William Fedus and William Saunders and William Zhang and W Vossen and Xiang Ren and Xiaoyu F Tong and Xinyi Wu and Xudong Shen and Yadollah Yaghoobzadeh and Yair Lakretz and Yang Song and Yasaman Bahri and Ye Ji Choi and Yichi Yang and Yiding Hao and Yifu Chen and Yonatan Belinkov and Yu Hou and Yu Hou and Yushi Bai and Zachary Seid and Zhao Xinran and Zhuoye Zhao and Zi Fu Wang and Zijie J. Wang and Zirui Wang and Ziyi Wu and Sahib Singh and Uri Shaham}, journal={ArXiv}, year={2022}, volume={abs/2206.04615} }
This task aims to measure the ability of computational models to understand short narratives, by identifying the most appropriate moral for a given fable from a set of five alternatives.
false
73
false
demelin/understanding_fables
2022-07-17T15:04:16.000Z
null
false
75280a8f3926668982a17d970708c325a412e0b9
[]
[ "arxiv:2206.04615", "annotations_creators:no-annotation", "language:en", "language_creators:expert-generated", "license:mit", "multilinguality:monolingual", "size_categories:n<1K", "source_datasets:original", "task_categories:multiple-choice", "task_categories:text-generation", "task_ids:multipl...
https://huggingface.co/datasets/demelin/understanding_fables/resolve/main/README.md
--- annotations_creators: - no-annotation language: - en language_creators: - expert-generated license: - mit multilinguality: - monolingual pretty_name: Understanding Fables size_categories: - n<1K source_datasets: - original task_categories: - multiple-choice - text-generation - text-understanding - text-comprehension - natural-language-understanding - natural-language-generation task_ids: - multiple-choice-qa - language-modeling --- # Dataset Card for Understanding Fables ## Table of Contents - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-instances) - [Data Splits](#data-instances) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) ## Dataset Description - **Homepage:** [Understanding Fables BIG-Bench entry](https://github.com/google/BIG-bench/tree/main/bigbench/benchmark_tasks/understanding_fables) - **Repository:** [Understanding Fables BIG-Bench entry](https://github.com/google/BIG-bench/tree/main/bigbench/benchmark_tasks/understanding_fables) - **Paper:** [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://arxiv.org/abs/2206.04615) - **Leaderboard:** [N/A] - **Point of Contact:** [Denis Emelin](demelin.github.io) ### Dataset Summary Fables are short narratives that aim to communicate a specific lesson or wisdom, referred to as the moral. Morals can be idiomatic or provide a succinct summary of the fable. Importantly, they make explicit the communicative intent of the fable and, thus, are highly relevant to its content. A computational model capable of natural language understanding should, when presented with a fable and a set of potentially relevant morals, rank the moral that accurately captures the message communicated by the fable above the rest. Additionally, fables represent a highly unusual narrative domain, where animals and inanimate objects are anthropomorphized and referred to with gendered pronouns, i.e., a rabbit may be a she, rather than an it. Thus, to understand fables, models must abstract away from patterns commonly encountered in their training data by applying human-like characteristics to non-human actors. Overall, for a computational model to perform well on this task, it must be capable of (1) successfully identifying the core message of a short narrative, (2) identifying a moral that expresses this message among a set of distractor morals, and (3) doing so within a narrative domain that is unlike the majority of pre-training data. Thus, the evaluated large language models would need to demonstrate cross-domain generalization capability in addition to narrative comprehension. The dataset evaluates models' ability to comprehend written narratives by asking them to select the most appropriate moral for each fable, from a set of five alternatives. In addition to the correct answer, this set contains four distractor morals, which were selected semi-automatically. To identify challenging distractor morals for each fable, sentence similarity was computed between the embeddings of each sentence in the fable and all morals found in the entire dataset, keeping ten morals that were found to be most similar to any of the fable's sentences. From this set, four distractors were selected manually, so that neither of the final distractors represents a valid moral of the fable. By construction, such distractor items are likely to pose a challenge for models that disproportionally rely on shallow heuristics as opposed to more sophisticated language-understanding strategies. ### Supported Tasks and Leaderboards - multiple-choice: The dataset can be used to evaluate models on their ability to rank a moral that is relevant to a specified fable above distractor morals, e.g. by assigning the correct choice a lower model perplexity. A [RoBERTa-based model](https://huggingface.co/roberta-base) can be used for this purpose. - text-generation: The dataset can also be used to train models to generate appropriate morals conditioned on the fable text. A [GPT-based model](https://huggingface.co/EleutherAI/gpt-neo-2.7B) can be used for this purpose. ### Languages The text in the dataset is in contemporary American English. ## Dataset Structure ### Data Instances A typical data point consists of a single fable, five morals - four distractors and one that correctly captures the lesson imparted by the fable, and an integer label denoting the ID of the correct answer option. An example dataset entry looks as follows: {"story": "On a warm winter's day, the ants were busy drying corn that they had collected during summer. While they were engaged in their work, a starving grasshopper passed by and begged them for a single grain to stop his hunger. The ants, in turn, asked him why he had not collected food during the summer to prepare for the harsh winter, to which the grasshopper replied that he spent the warm days singing. Mockingly, the ants said to him in unison: "Since you spent your summer singing, then you must dance hungrily to bed in winter." What is the moral of this story?", "answer0": "Fine clothes may disguise, but silly words will disclose a fool.", "answer1": "Better starve free than be a fat slave.", "answer2": "Evil wishes, like chickens, come home to roost.", "answer3": "Grasp at the shadow and you will lose the substance.", "answer4": "It is thrifty to prepare today for the wants of tomorrow.", "label": 4} ### Data Fields - "story': The fable for which the appropriate moral has to be identified - "answerN": Moral candidates to be evaluated by the model - "label": The ID of the moral belonging to the fable ### Data Splits *Understanding Fables* was designed as an evaluation-only benchmark and therefore is intended to be used for zero-shot testing only. However, users are very welcome to split the data as they wish :) . ## Dataset Creation ### Curation Rationale To comply with the requirements for inclusion in BIG-bench, each fable was manually paraphrased, to ensure that the task cannot be solved by memorising web data. Following sources were used for fable collection: - [https://www.aesopfables.com/aesop1.html](https://www.aesopfables.com/aesop1.html) - [https://www.aesopfables.com/aesop2.html](https://www.aesopfables.com/aesop2.html) - [https://www.aesopfables.com/aesop3.html](https://www.aesopfables.com/aesop3.html) - [https://www.aesopfables.com/aesop4.html](https://www.aesopfables.com/aesop4.html) ### Source Data #### Initial Data Collection and Normalization Paraphrasing was done by an English speaker with native-like language proficiency and an academic background in literature. The created paraphrases differ from the originals in the identity of their participants (lion was replaced with tiger, wolf with coyote etc.), their sentence and narrative structure, and their register (archaic terms such as thou have been replaced with their modern counterparts). The phrasing of the morals has also been updated in cases where the original language was noticeably archaic (e.g., o'er reach -> overreach), with changes kept to a minimum. The mean string similarity between original fables and their paraphrases is consequently low at 0.26, according to the word-level DamerauLevenshtein distance. At the same time, great care was taken not to alter the content of the fables and preserve the relevance of their respective morals. This is evidenced by the high semantic similarity between the originals and their paraphrases, with a mean of 0.78, computed as the cosine similarity between the embeddings of the originals and their paraphrases, obtained using the Sentence-Transformers library. Moreover, duplicate and near-duplicate fables were removed from the final collection, as were several thematically problematic stories, e.g., ones with sexist undertones. In total, the dataset includes 189 paraphrased, unique fables. #### Who are the source language producers? Original authors and transcribers of the fables (unknown), the [dataset author](demelin.github.io). ### Annotations #### Annotation process [N/A] #### Who are the annotators? [N/A] ### Personal and Sensitive Information [N/A] ## Considerations for Using the Data ### Social Impact of Dataset [N/A] ### Discussion of Biases Several thematically problematic fables, e.g., ones with sexist undertones, were removed by the author during the dataset creation process. However, it can be that the author overlooked other problematic or harmful biases present within the dataset. ### Other Known Limitations The dataset is very limited in size due to the small number of thematically distinct fables available online. Similarly, the focus on English fables alone is a limiting factor to be addressed in future dataset iterations. ## Additional Information ### Dataset Curators [Denis Emelin](demelin.github.io) ### Licensing Information MIT ### Citation Information @article{Srivastava2022BeyondTI, title={Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models}, author={Aarohi Srivastava and Abhinav Rastogi and Abhishek B Rao and Abu Awal Md Shoeb and Abubakar Abid and Adam Fisch and Adam R. Brown and Adam Santoro and Aditya Gupta and Adri{\`a} Garriga-Alonso and Agnieszka Kluska and Aitor Lewkowycz and Akshat Agarwal and Alethea Power and Alex Ray and Alex Warstadt and Alexander W. Kocurek and Ali Safaya and Ali Tazarv and Alice Xiang and Alicia Parrish and Allen Nie and Aman Hussain and Amanda Askell and Amanda Dsouza and Ameet Annasaheb Rahane and Anantharaman S. Iyer and Anders Johan Andreassen and Andrea Santilli and Andreas Stuhlmuller and Andrew M. Dai and Andrew D. La and Andrew Kyle Lampinen and Andy Zou and Angela Jiang and Angelica Chen and Anh Vuong and Animesh Gupta and Anna Gottardi and Antonio Norelli and Anu Venkatesh and Arash Gholamidavoodi and Arfa Tabassum and Arul Menezes and Arun Kirubarajan and Asher Mullokandov and Ashish Sabharwal and Austin Herrick and Avia Efrat and Aykut Erdem and Ayla Karakacs and Bridget R. Roberts and Bao Sheng Loe and Barret Zoph and Bartlomiej Bojanowski and Batuhan Ozyurt and Behnam Hedayatnia and Behnam Neyshabur and Benjamin Inden and Benno Stein and Berk Ekmekci and Bill Yuchen Lin and Blake Stephen Howald and Cameron Diao and Cameron Dour and Catherine Stinson and Cedrick Argueta and C'esar Ferri Ram'irez and Chandan Singh and Charles Rathkopf and Chenlin Meng and Chitta Baral and Chiyu Wu and Chris Callison-Burch and Chris Waites and Christian Voigt and Christopher D. Manning and Christopher Potts and Cindy Tatiana Ramirez and Clara Rivera and Clemencia Siro and Colin Raffel and Courtney Ashcraft and Cristina Garbacea and Damien Sileo and Daniel H Garrette and Dan Hendrycks and Dan Kilman and Dan Roth and Daniel Freeman and Daniel Khashabi and Daniel Levy and Daniel Gonz'alez and Danny Hernandez and Danqi Chen and Daphne Ippolito and Dar Gilboa and David Dohan and D. Drakard and David Jurgens and Debajyoti Datta and Deep Ganguli and Denis Emelin and Denis Kleyko and Deniz Yuret and Derek Chen and Derek Tam and Dieuwke Hupkes and Diganta Misra and Dilyar Buzan and Dimitri Coelho Mollo and Diyi Yang and Dong-Ho Lee and Ekaterina Shutova and Ekin Dogus Cubuk and Elad Segal and Eleanor Hagerman and Elizabeth Barnes and Elizabeth P. Donoway and Ellie Pavlick and Emanuele Rodol{\`a} and Emma FC Lam and Eric Chu and Eric Tang and Erkut Erdem and Ernie Chang and Ethan A. Chi and Ethan Dyer and Ethan Jerzak and Ethan Kim and Eunice Engefu Manyasi and Evgenii Zheltonozhskii and Fan Xia and Fatemeh Siar and Fernando Mart'inez-Plumed and Francesca Happ'e and François Chollet and Frieda Rong and Gaurav Mishra and Genta Indra Winata and Gerard de Melo and Germ{\'a}n Kruszewski and Giambattista Parascandolo and Giorgio Mariani and Gloria Wang and Gonzalo Jaimovitch-L'opez and Gregor Betz and Guy Gur-Ari and Hana Galijasevic and Han Sol Kim and Hannah Rashkin and Hanna Hajishirzi and Harsh Mehta and Hayden Bogar and Henry Shevlin and Hinrich Sch{\"u}tze and Hiromu Yakura and Hongming Zhang and Hubert Wong and Ian Aik-Soon Ng and Isaac Noble and Jaap Jumelet and Jack Geissinger and John Kernion and Jacob Hilton and Jaehoon Lee and Jaime Fern{\'a}ndez Fisac and J. Brooker Simon and James Koppel and James Zheng and James Zou and Jan Koco'n and Jana Thompson and Jared Kaplan and Jarema Radom and Jascha Narain Sohl-Dickstein and Jason Phang and Jason Wei and Jason Yosinski and Jekaterina Novikova and Jelle Bosscher and Jenni Marsh and Jeremy Kim and Jeroen Taal and Jesse Engel and Jesujoba Oluwadara Alabi and Jiacheng Xu and Jiaming Song and Jillian Tang and Jane W Waweru and John Burden and John Miller and John U. Balis and Jonathan Berant and Jorg Frohberg and Jos Rozen and Jos{\'e} Hern{\'a}ndez-Orallo and Joseph Boudeman and Joseph Jones and Joshua B. Tenenbaum and Joshua S. Rule and Joyce Chua and Kamil Kanclerz and Karen Livescu and Karl Krauth and Karthik Gopalakrishnan and Katerina Ignatyeva and Katja Markert and Kaustubh D. Dhole and Kevin Gimpel and Kevin Ochieng’ Omondi and Kory Wallace Mathewson and Kristen Chiafullo and Ksenia Shkaruta and Kumar Shridhar and Kyle McDonell and Kyle Richardson and Laria Reynolds and Leo Gao and Li Zhang and Liam Dugan and Lianhui Qin and Lidia Contreras-Ochando and Louis-Philippe Morency and Luca Moschella and Luca Lam and Lucy Noble and Ludwig Schmidt and Luheng He and Luis Oliveros Col'on and Luke Metz and Lutfi Kerem cSenel and Maarten Bosma and Maarten Sap and Maartje ter Hoeve and Madotto Andrea and Maheen Saleem Farooqi and Manaal Faruqui and Mantas Mazeika and Marco Baturan and Marco Marelli and Marco Maru and M Quintana and Marie Tolkiehn and Mario Giulianelli and Martha Lewis and Martin Potthast and Matthew Leavitt and Matthias Hagen and M'aty'as Schubert and Medina Baitemirova and Melissa Arnaud and Melvin Andrew McElrath and Michael A. Yee and Michael Cohen and Mi Gu and Michael I. Ivanitskiy and Michael Starritt and Michael Strube and Michal Swkedrowski and Michele Bevilacqua and Michihiro Yasunaga and Mihir Kale and Mike Cain and Mimee Xu and Mirac Suzgun and Monica Tiwari and Mohit Bansal and Moin Aminnaseri and Mor Geva and Mozhdeh Gheini and T MukundVarma and Nanyun Peng and Nathan Chi and Nayeon Lee and Neta Gur-Ari Krakover and Nicholas Cameron and Nicholas S. Roberts and Nicholas Doiron and Nikita Nangia and Niklas Deckers and Niklas Muennighoff and Nitish Shirish Keskar and Niveditha Iyer and Noah Constant and Noah Fiedel and Nuan Wen and Oliver Zhang and Omar Agha and Omar Elbaghdadi and Omer Levy and Owain Evans and Pablo Antonio Moreno Casares and Parth Doshi and Pascale Fung and Paul Pu Liang and Paul Vicol and Pegah Alipoormolabashi and Peiyuan Liao and Percy Liang and Peter W. Chang and Peter Eckersley and Phu Mon Htut and Pi-Bei Hwang and P. Milkowski and Piyush S. Patil and Pouya Pezeshkpour and Priti Oli and Qiaozhu Mei and QING LYU and Qinlang Chen and Rabin Banjade and Rachel Etta Rudolph and Raefer Gabriel and Rahel Habacker and Ram'on Risco Delgado and Rapha{\"e}l Milli{\`e}re and Rhythm Garg and Richard Barnes and Rif A. Saurous and Riku Arakawa and Robbe Raymaekers and Robert Frank and Rohan Sikand and Roman Novak and Roman Sitelew and Ronan Le Bras and Rosanne Liu and Rowan Jacobs and Rui Zhang and Ruslan Salakhutdinov and Ryan Chi and Ryan Lee and Ryan Stovall and Ryan Teehan and Rylan Yang and Sahib J. Singh and Saif M. Mohammad and Sajant Anand and Sam Dillavou and Sam Shleifer and Sam Wiseman and Samuel Gruetter and Sam Bowman and Samuel S. Schoenholz and Sanghyun Han and Sanjeev Kwatra and Sarah A. Rous and Sarik Ghazarian and Sayan Ghosh and Sean Casey and Sebastian Bischoff and Sebastian Gehrmann and Sebastian Schuster and Sepideh Sadeghi and Shadi Sameh Hamdan and Sharon Zhou and Shashank Srivastava and Sherry Shi and Shikhar Singh and Shima Asaadi and Shixiang Shane Gu and Shubh Pachchigar and Shubham Toshniwal and Shyam Upadhyay and Shyamolima Debnath and Siamak Shakeri and Simon Thormeyer and Simone Melzi and Siva Reddy and Sneha Priscilla Makini and Soo-hwan Lee and Spencer Bradley Torene and Sriharsha Hatwar and Stanislas Dehaene and Stefan Divic and Stefano Ermon and Stella Rose Biderman and Stephanie C. Lin and Stephen Prasad and Steven T. Piantadosi and Stuart M. Shieber and Summer Misherghi and Svetlana Kiritchenko and Swaroop Mishra and Tal Linzen and Tal Schuster and Tao Li and Tao Yu and Tariq A. Ali and Tatsuo Hashimoto and Te-Lin Wu and Theo Desbordes and Theodore Rothschild and Thomas Phan and Tianle Wang and Tiberius Nkinyili and Timo Schick and T. N. Kornev and Timothy Telleen-Lawton and Titus Tunduny and Tobias Gerstenberg and Trenton Chang and Trishala Neeraj and Tushar Khot and Tyler O. Shultz and Uri Shaham and Vedant Misra and Vera Demberg and Victoria Nyamai and Vikas Raunak and Vinay V. Ramasesh and Vinay Uday Prabhu and Vishakh Padmakumar and Vivek Srikumar and William Fedus and William Saunders and William Zhang and W Vossen and Xiang Ren and Xiaoyu F Tong and Xinyi Wu and Xudong Shen and Yadollah Yaghoobzadeh and Yair Lakretz and Yang Song and Yasaman Bahri and Ye Ji Choi and Yichi Yang and Yiding Hao and Yifu Chen and Yonatan Belinkov and Yu Hou and Yu Hou and Yushi Bai and Zachary Seid and Zhao Xinran and Zhuoye Zhao and Zi Fu Wang and Zijie J. Wang and Zirui Wang and Ziyi Wu and Sahib Singh and Uri Shaham}, journal={ArXiv}, year={2022}, volume={abs/2206.04615} }
ArthurBaia
null
@article{2016arXiv160605250R, author = {{Rajpurkar}, Pranav and {Zhang}, Jian and {Lopyrev}, Konstantin and {Liang}, Percy}, title = "{SQuAD: 100,000+ Questions for Machine Comprehension of Text}", journal = {arXiv e-prints}, year = 2016, eid = {arXiv:1606.05250}, pages = {arXiv:1606.05250}, archivePrefix = {arXiv}, eprint = {1606.05250}, }
This dataset was translated by Deep Learning Brazil
false
7
false
ArthurBaia/squad_v1_pt_br
2022-11-09T15:34:43.000Z
null
false
3221702053e2bb473803a6fc25db782035951405
[]
[]
https://huggingface.co/datasets/ArthurBaia/squad_v1_pt_br/resolve/main/README.md
This dataset was created by Deep Learning Brasil(www.deeplearningbrasil.com.br). I just published it on Hugging Face hub with the intention to share it with more people that are training brazilian portuguese models. The original link is here drive.google.com/file/d/1Q0IaIlv2h2BC468MwUFmUST0EyN7gNkn/view.
cannlytics
null
null
null
false
1
false
cannlytics/aggregated-cannabis-test-results
2022-07-16T01:13:36.000Z
null
false
c815501a8be2ae962d5a113fd4b5ed87a19467ae
[]
[ "license:cc-by-4.0" ]
https://huggingface.co/datasets/cannlytics/aggregated-cannabis-test-results/resolve/main/README.md
--- license: cc-by-4.0 --- # Aggregated Cannabis Laboratory Test Results Lab results are arguably among the most valuable data that you can come by in the cannabis industry. Due to the complexity of the data and, until now, a lack of standardization, the lab results that are publicly available have been just out of reach. Cannlytics puts these lab results in your hands, fresh, clean, and standardized, ripe for you to calculate juicy cannabis statistics. ## Algorithms | Algorithm | URL | |-----------|-----| | MCR Labs Data Collection Routine | <https://github.com/cannlytics/cannlytics/tree/main/ai/curation/get_mcr_labs_data> | | PSI Labs Data Collection Routine | <https://github.com/cannlytics/cannlytics/tree/main/ai/curation/get_psi_labs_data> | | SC Labs Data Collection Routine | <https://github.com/cannlytics/cannlytics/tree/main/ai/curation/get_sc_labs_data> | ## Data Sources | Data Source | URL | |-------------|-----| | MCR Labs Test Results | <https://reports.mcrlabs.com> | | PSI Labs Test Results | <https://results.psilabs.org/test-results/> | | SC Labs Test Results | <https://client.sclabs.com/> ## License ``` Copyright (c) 2022 Cannlytics and the Cannabis Data Science Team The files associated with this dataset are licensed under a Creative Commons Attribution 4.0 International license. You can share, copy and modify this dataset so long as you give appropriate credit, provide a link to the CC BY license, and indicate if changes were made, but you may not do so in a way that suggests the rights holder has endorsed you or your use of the dataset. Note that further permission may be required for any content within the dataset that is identified as belonging to a third party. ```
colbertv2
null
@inproceedings{santhanam-etal-2022-colbertv2, title = "{C}ol{BERT}v2: Effective and Efficient Retrieval via Lightweight Late Interaction", author = "Santhanam, Keshav and Khattab, Omar and Saad-Falcon, Jon and Potts, Christopher and Zaharia, Matei", booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies", month = jul, year = "2022", address = "Seattle, United States", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2022.naacl-main.272", pages = "3715--3734", abstract = "Neural information retrieval (IR) has greatly advanced search and other knowledge-intensive language tasks. While many neural IR methods encode queries and documents into single-vector representations, late interaction models produce multi-vector representations at the granularity of each token and decompose relevance modeling into scalable token-level computations. This decomposition has been shown to make late interaction more effective, but it inflates the space footprint of these models by an order of magnitude. In this work, we introduce Maize, a retriever that couples an aggressive residual compression mechanism with a denoised supervision strategy to simultaneously improve the quality and space footprint of late interaction. We evaluate Maize across a wide range of benchmarks, establishing state-of-the-art quality within and outside the training domain while reducing the space footprint of late interaction models by 6{--}10x.", }
LoTTE Passages Dataset for ColBERTv2
false
1
false
colbertv2/lotte
2022-08-04T17:55:59.000Z
null
false
1a87807da631e4197d77f7e720c38941abcf26d1
[]
[ "arxiv:2112.01488", "annotations_creators:no-annotation", "language:en", "language_creators:found", "license:apache-2.0", "multilinguality:monolingual", "size_categories:10K<n<100K", "source_datasets:original", "task_categories:question-answering", "task_ids:extractive-qa" ]
https://huggingface.co/datasets/colbertv2/lotte/resolve/main/README.md
--- annotations_creators: - no-annotation language: - en language_creators: - found license: - apache-2.0 multilinguality: - monolingual pretty_name: 'Lotte queries from ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction' size_categories: - 10K<n<100K source_datasets: - original tags: [] task_categories: - question-answering task_ids: - extractive-qa --- Queries for Lotte dataset from [ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction](https://arxiv.org/abs/2112.01488)
colbertv2
null
@inproceedings{santhanam-etal-2022-colbertv2, title = "{C}ol{BERT}v2: Effective and Efficient Retrieval via Lightweight Late Interaction", author = "Santhanam, Keshav and Khattab, Omar and Saad-Falcon, Jon and Potts, Christopher and Zaharia, Matei", booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies", month = jul, year = "2022", address = "Seattle, United States", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2022.naacl-main.272", pages = "3715--3734", abstract = "Neural information retrieval (IR) has greatly advanced search and other knowledge-intensive language tasks. While many neural IR methods encode queries and documents into single-vector representations, late interaction models produce multi-vector representations at the granularity of each token and decompose relevance modeling into scalable token-level computations. This decomposition has been shown to make late interaction more effective, but it inflates the space footprint of these models by an order of magnitude. In this work, we introduce Maize, a retriever that couples an aggressive residual compression mechanism with a denoised supervision strategy to simultaneously improve the quality and space footprint of late interaction. We evaluate Maize across a wide range of benchmarks, establishing state-of-the-art quality within and outside the training domain while reducing the space footprint of late interaction models by 6{--}10x.", }
LoTTE Passages Dataset for ColBERTv2
false
3
false
colbertv2/lotte_passages
2022-08-04T18:04:07.000Z
null
false
3217cce4888ac8bcc074d1b250836d3521e74ca2
[]
[ "arxiv:2112.01488", "annotations_creators:no-annotation", "language:en", "language_creators:found", "license:apache-2.0", "multilinguality:monolingual", "size_categories:1M<n<10M", "source_datasets:original", "task_categories:question-answering", "task_ids:extractive-qa" ]
https://huggingface.co/datasets/colbertv2/lotte_passages/resolve/main/README.md
--- annotations_creators: - no-annotation language: - en language_creators: - found license: - apache-2.0 multilinguality: - monolingual pretty_name: 'Lotte passages from ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction' size_categories: - 1M<n<10M source_datasets: - original tags: [] task_categories: - question-answering task_ids: - extractive-qa --- Passages for the LoTTe dataset used for [ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction](https://arxiv.org/abs/2112.01488)
wjddmlfud
null
null
null
false
1
false
wjddmlfud/sample_dataaset
2022-07-15T02:45:23.000Z
null
false
fe64fb6e160cef79ce72ce213ad449e1bf084bf1
[]
[ "license:afl-3.0" ]
https://huggingface.co/datasets/wjddmlfud/sample_dataaset/resolve/main/README.md
--- license: afl-3.0 ---
Raagul04
null
null
null
false
1
false
Raagul04/DocVQA_train
2022-07-15T06:54:18.000Z
null
false
069ea5adedc59024af9dcb5ac0655604ad11681f
[]
[ "license:afl-3.0" ]
https://huggingface.co/datasets/Raagul04/DocVQA_train/resolve/main/README.md
--- license: afl-3.0 ---
autoevaluate
null
null
null
false
1
false
autoevaluate/autoeval-staging-eval-project-samsum-f90fd7b5-10915466
2022-07-15T09:35:16.000Z
null
false
82958bf09d7d89df4057f4da29070ce88fb57b61
[]
[ "type:predictions", "tags:autotrain", "tags:evaluation", "datasets:samsum" ]
https://huggingface.co/datasets/autoevaluate/autoeval-staging-eval-project-samsum-f90fd7b5-10915466/resolve/main/README.md
--- type: predictions tags: - autotrain - evaluation datasets: - samsum eval_info: task: summarization model: pszemraj/led-large-book-summary metrics: ['bleu'] dataset_name: samsum dataset_config: samsum dataset_split: test col_mapping: text: dialogue target: summary --- # Dataset Card for AutoTrain Evaluator This repository contains model predictions generated by [AutoTrain](https://huggingface.co/autotrain) for the following task and dataset: * Task: Summarization * Model: pszemraj/led-large-book-summary * Dataset: samsum * Config: samsum * Split: test To run new evaluation jobs, visit Hugging Face's [automatic model evaluator](https://huggingface.co/spaces/autoevaluate/model-evaluator). ## Contributions Thanks to [@pszemraj](https://huggingface.co/pszemraj) for evaluating this model.
autoevaluate
null
null
null
false
1
false
autoevaluate/autoeval-staging-eval-project-samsum-f4288f9c-10925467
2022-07-15T09:38:05.000Z
null
false
017454cddb5c85def8062c929f4361b50f4491e8
[]
[ "type:predictions", "tags:autotrain", "tags:evaluation", "datasets:samsum" ]
https://huggingface.co/datasets/autoevaluate/autoeval-staging-eval-project-samsum-f4288f9c-10925467/resolve/main/README.md
--- type: predictions tags: - autotrain - evaluation datasets: - samsum eval_info: task: summarization model: pszemraj/led-base-book-summary metrics: ['bleu'] dataset_name: samsum dataset_config: samsum dataset_split: test col_mapping: text: dialogue target: summary --- # Dataset Card for AutoTrain Evaluator This repository contains model predictions generated by [AutoTrain](https://huggingface.co/autotrain) for the following task and dataset: * Task: Summarization * Model: pszemraj/led-base-book-summary * Dataset: samsum * Config: samsum * Split: test To run new evaluation jobs, visit Hugging Face's [automatic model evaluator](https://huggingface.co/spaces/autoevaluate/model-evaluator). ## Contributions Thanks to [@pszemraj](https://huggingface.co/pszemraj) for evaluating this model.
autoevaluate
null
null
null
false
1
false
autoevaluate/autoeval-staging-eval-project-cnn_dailymail-899c0b5b-10935468
2022-07-16T13:52:25.000Z
null
false
936e8aef739add279dfb20352a24bfb9d388949f
[]
[ "type:predictions", "tags:autotrain", "tags:evaluation", "datasets:cnn_dailymail" ]
https://huggingface.co/datasets/autoevaluate/autoeval-staging-eval-project-cnn_dailymail-899c0b5b-10935468/resolve/main/README.md
--- type: predictions tags: - autotrain - evaluation datasets: - cnn_dailymail eval_info: task: summarization model: pszemraj/led-base-book-summary metrics: ['bleu'] dataset_name: cnn_dailymail dataset_config: 3.0.0 dataset_split: test col_mapping: text: article target: highlights --- # Dataset Card for AutoTrain Evaluator This repository contains model predictions generated by [AutoTrain](https://huggingface.co/autotrain) for the following task and dataset: * Task: Summarization * Model: pszemraj/led-base-book-summary * Dataset: cnn_dailymail * Config: 3.0.0 * Split: test To run new evaluation jobs, visit Hugging Face's [automatic model evaluator](https://huggingface.co/spaces/autoevaluate/model-evaluator). ## Contributions Thanks to [@pszemraj](https://huggingface.co/pszemraj) for evaluating this model.
MariaIsabel
null
null
null
false
1
false
MariaIsabel/FR_NFR_Spanish_requirements_classification
2022-07-22T07:19:16.000Z
null
false
89b36b13527a745815e20ec785ddf270c52e64fc
[]
[ "annotations_creators:other", "language:es", "language_creators:other", "license:cc-by-4.0", "multilinguality:monolingual", "size_categories:10K<n<100K", "source_datasets:original", "task_categories:text-classification", "task_ids:multi-class-classification" ]
https://huggingface.co/datasets/MariaIsabel/FR_NFR_Spanish_requirements_classification/resolve/main/README.md
--- annotations_creators: - other language: - es language_creators: - other license: - cc-by-4.0 multilinguality: - monolingual pretty_name: Spanish requirements labeled in functional and non-functional classes. size_categories: - 10K<n<100K source_datasets: - original task_categories: - text-classification task_ids: - multi-class-classification --- ## Dataset Description - **Homepage:** - **Repository:** - **Paper:** - **Leaderboard:** - **Point of Contact:** ### Dataset Summary Published version of dataset used for paper 'Towards an automatic requirements classification in a new Spanish dataset' ### Languages Spanish ## Dataset Structure ### Data Fields Project: Project's Identifier from which the requirements were obtained. Requirement: Description of the software requirement. Final label: Label of the requirement: F (functional requirement) and NF (non-functional requirement). ## Dataset Creation ### Initial Data Collection and Normalization This dataset was created from a collection of functional and non-functional requirements extracted from 13 final degree and 2 master’s projects carried out from the University of A Coruna. It consist in 300 functional and 89 non-funtcional requirements. ## Additional Information ### Citation Information https://doi.org/10.5281/zenodo.6556541
yongjian
null
null
null
false
22
false
yongjian/music-clips-50
2022-10-07T14:21:39.000Z
null
false
5157310f019772611e38adb57ce1ebe589a1f2d0
[]
[ "multilinguality:other-music", "language:en", "language:zh" ]
https://huggingface.co/datasets/yongjian/music-clips-50/resolve/main/README.md
--- pretty_name: music-clips-50 multilinguality: - other-music language: - en - zh --- There are 50 music clips(of 3~5 seconds). You can load them by the following code: ```python from datasets import load_dataset dataset = load_dataset('yongjian/music-clips-50') clips = dataset['train'] # all 50 music clips music_1_np_array = clips[0]['audio']['array'] # numpy array of shape=[N,] ``` Or you can directly download them from Google Drive: [music-clips-50.tar.gz](https://drive.google.com/file/d/154y_Z9p1Sfhrwzj7jc46UMbTaAmI17AT/view?usp=sharing).
autoevaluate
null
null
null
false
1
false
autoevaluate/autoeval-staging-eval-project-cnn_dailymail-b5ccd808-10945470
2022-07-16T20:06:13.000Z
null
false
2dedccea0d29e34b977e54a4e3a9b106cfde86a3
[]
[ "type:predictions", "tags:autotrain", "tags:evaluation", "datasets:cnn_dailymail" ]
https://huggingface.co/datasets/autoevaluate/autoeval-staging-eval-project-cnn_dailymail-b5ccd808-10945470/resolve/main/README.md
--- type: predictions tags: - autotrain - evaluation datasets: - cnn_dailymail eval_info: task: summarization model: pszemraj/long-t5-tglobal-base-16384-book-summary metrics: ['bleu'] dataset_name: cnn_dailymail dataset_config: 3.0.0 dataset_split: test col_mapping: text: article target: highlights --- # Dataset Card for AutoTrain Evaluator This repository contains model predictions generated by [AutoTrain](https://huggingface.co/autotrain) for the following task and dataset: * Task: Summarization * Model: pszemraj/long-t5-tglobal-base-16384-book-summary * Dataset: cnn_dailymail * Config: 3.0.0 * Split: test To run new evaluation jobs, visit Hugging Face's [automatic model evaluator](https://huggingface.co/spaces/autoevaluate/model-evaluator). ## Contributions Thanks to [@pszemraj](https://huggingface.co/pszemraj) for evaluating this model.
autoevaluate
null
null
null
false
1
false
autoevaluate/autoeval-staging-eval-project-emotion-d66bcc95-10955472
2022-07-15T12:46:34.000Z
null
false
48c0cf425bd9298d153cafcaf02a9c9fc492c74f
[]
[ "type:predictions", "tags:autotrain", "tags:evaluation", "datasets:emotion" ]
https://huggingface.co/datasets/autoevaluate/autoeval-staging-eval-project-emotion-d66bcc95-10955472/resolve/main/README.md
--- type: predictions tags: - autotrain - evaluation datasets: - emotion eval_info: task: multi_class_classification model: Abdelrahman-Rezk/distilbert-base-uncased-finetuned-emotion metrics: [] dataset_name: emotion dataset_config: default dataset_split: test col_mapping: text: text target: label --- # Dataset Card for AutoTrain Evaluator This repository contains model predictions generated by [AutoTrain](https://huggingface.co/autotrain) for the following task and dataset: * Task: Multi-class Text Classification * Model: Abdelrahman-Rezk/distilbert-base-uncased-finetuned-emotion * Dataset: emotion * Config: default * Split: test To run new evaluation jobs, visit Hugging Face's [automatic model evaluator](https://huggingface.co/spaces/autoevaluate/model-evaluator). ## Contributions Thanks to [@postpandas](https://huggingface.co/postpandas) for evaluating this model.
autoevaluate
null
null
null
false
6
false
autoevaluate/autoeval-staging-eval-project-kmfoda__booksum-5034faac-10965473
2022-07-16T08:47:50.000Z
null
false
1e31c791f31b55f5caec82618f5a69bf8471b9bc
[]
[ "type:predictions", "tags:autotrain", "tags:evaluation", "datasets:kmfoda/booksum" ]
https://huggingface.co/datasets/autoevaluate/autoeval-staging-eval-project-kmfoda__booksum-5034faac-10965473/resolve/main/README.md
--- type: predictions tags: - autotrain - evaluation datasets: - kmfoda/booksum eval_info: task: summarization model: pszemraj/bigbird-pegasus-large-K-booksum metrics: ['perplexity'] dataset_name: kmfoda/booksum dataset_config: kmfoda--booksum dataset_split: test col_mapping: text: chapter target: summary_text --- # Dataset Card for AutoTrain Evaluator This repository contains model predictions generated by [AutoTrain](https://huggingface.co/autotrain) for the following task and dataset: * Task: Summarization * Model: pszemraj/bigbird-pegasus-large-K-booksum * Dataset: kmfoda/booksum * Config: kmfoda--booksum * Split: test To run new evaluation jobs, visit Hugging Face's [automatic model evaluator](https://huggingface.co/spaces/autoevaluate/model-evaluator). ## Contributions Thanks to [@pszemraj](https://huggingface.co/pszemraj) for evaluating this model.
autoevaluate
null
null
null
false
1
false
autoevaluate/autoeval-staging-eval-project-kmfoda__booksum-e703e34d-10975474
2022-07-15T22:33:56.000Z
null
false
716d9abaf7748fc0e34bef0986e4d3fba174f78c
[]
[ "type:predictions", "tags:autotrain", "tags:evaluation", "datasets:kmfoda/booksum" ]
https://huggingface.co/datasets/autoevaluate/autoeval-staging-eval-project-kmfoda__booksum-e703e34d-10975474/resolve/main/README.md
--- type: predictions tags: - autotrain - evaluation datasets: - kmfoda/booksum eval_info: task: summarization model: pszemraj/long-t5-tglobal-base-16384-book-summary metrics: [] dataset_name: kmfoda/booksum dataset_config: kmfoda--booksum dataset_split: test col_mapping: text: chapter target: summary_text --- # Dataset Card for AutoTrain Evaluator This repository contains model predictions generated by [AutoTrain](https://huggingface.co/autotrain) for the following task and dataset: * Task: Summarization * Model: pszemraj/long-t5-tglobal-base-16384-book-summary * Dataset: kmfoda/booksum * Config: kmfoda--booksum * Split: test To run new evaluation jobs, visit Hugging Face's [automatic model evaluator](https://huggingface.co/spaces/autoevaluate/model-evaluator). ## Contributions Thanks to [@pszemraj](https://huggingface.co/pszemraj) for evaluating this model.
autoevaluate
null
null
null
false
6
false
autoevaluate/autoeval-staging-eval-project-kmfoda__booksum-39317f76-10985475
2022-07-16T17:30:51.000Z
null
false
dc6e99653f818c6020880a66cc94a3901bebd738
[]
[ "type:predictions", "tags:autotrain", "tags:evaluation", "datasets:kmfoda/booksum" ]
https://huggingface.co/datasets/autoevaluate/autoeval-staging-eval-project-kmfoda__booksum-39317f76-10985475/resolve/main/README.md
--- type: predictions tags: - autotrain - evaluation datasets: - kmfoda/booksum eval_info: task: summarization model: pszemraj/long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP metrics: [] dataset_name: kmfoda/booksum dataset_config: kmfoda--booksum dataset_split: test col_mapping: text: chapter target: summary_text --- # Dataset Card for AutoTrain Evaluator This repository contains model predictions generated by [AutoTrain](https://huggingface.co/autotrain) for the following task and dataset: * Task: Summarization * Model: pszemraj/long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP * Dataset: kmfoda/booksum * Config: kmfoda--booksum * Split: test To run new evaluation jobs, visit Hugging Face's [automatic model evaluator](https://huggingface.co/spaces/autoevaluate/model-evaluator). ## Contributions Thanks to [@pszemraj](https://huggingface.co/pszemraj) for evaluating this model.
autoevaluate
null
null
null
false
6
false
autoevaluate/autoeval-staging-eval-project-kmfoda__booksum-111b8468-10995476
2022-07-16T13:56:12.000Z
null
false
f0c22bfb495043277bdc0cd682946f7fb642ff87
[]
[ "type:predictions", "tags:autotrain", "tags:evaluation", "datasets:kmfoda/booksum" ]
https://huggingface.co/datasets/autoevaluate/autoeval-staging-eval-project-kmfoda__booksum-111b8468-10995476/resolve/main/README.md
--- type: predictions tags: - autotrain - evaluation datasets: - kmfoda/booksum eval_info: task: summarization model: pszemraj/pegasus-large-book-summary metrics: [] dataset_name: kmfoda/booksum dataset_config: kmfoda--booksum dataset_split: test col_mapping: text: chapter target: summary_text --- # Dataset Card for AutoTrain Evaluator This repository contains model predictions generated by [AutoTrain](https://huggingface.co/autotrain) for the following task and dataset: * Task: Summarization * Model: pszemraj/pegasus-large-book-summary * Dataset: kmfoda/booksum * Config: kmfoda--booksum * Split: test To run new evaluation jobs, visit Hugging Face's [automatic model evaluator](https://huggingface.co/spaces/autoevaluate/model-evaluator). ## Contributions Thanks to [@pszemraj](https://huggingface.co/pszemraj) for evaluating this model.
autoevaluate
null
null
null
false
1
false
autoevaluate/autoeval-staging-eval-project-emotion-21f117d5-11035480
2022-07-15T12:47:33.000Z
null
false
324635d6c6e6cd1affb2c09c89da530690c39d66
[]
[ "type:predictions", "tags:autotrain", "tags:evaluation", "datasets:emotion" ]
https://huggingface.co/datasets/autoevaluate/autoeval-staging-eval-project-emotion-21f117d5-11035480/resolve/main/README.md
--- type: predictions tags: - autotrain - evaluation datasets: - emotion eval_info: task: multi_class_classification model: jsoutherland/distilbert-base-uncased-finetuned-emotion metrics: [] dataset_name: emotion dataset_config: default dataset_split: test col_mapping: text: text target: label --- # Dataset Card for AutoTrain Evaluator This repository contains model predictions generated by [AutoTrain](https://huggingface.co/autotrain) for the following task and dataset: * Task: Multi-class Text Classification * Model: jsoutherland/distilbert-base-uncased-finetuned-emotion * Dataset: emotion * Config: default * Split: test To run new evaluation jobs, visit Hugging Face's [automatic model evaluator](https://huggingface.co/spaces/autoevaluate/model-evaluator). ## Contributions Thanks to [@jsoutherland](https://huggingface.co/jsoutherland) for evaluating this model.
autoevaluate
null
null
null
false
1
false
autoevaluate/autoeval-staging-eval-project-cnn_dailymail-f8e8ca08-11045481
2022-07-16T20:19:05.000Z
null
false
5cc5981e1b29fb7740e4c2b1eb9310e30c286048
[]
[ "type:predictions", "tags:autotrain", "tags:evaluation", "datasets:cnn_dailymail" ]
https://huggingface.co/datasets/autoevaluate/autoeval-staging-eval-project-cnn_dailymail-f8e8ca08-11045481/resolve/main/README.md
--- type: predictions tags: - autotrain - evaluation datasets: - cnn_dailymail eval_info: task: summarization model: pszemraj/long-t5-tglobal-base-16384-book-summary metrics: [] dataset_name: cnn_dailymail dataset_config: 3.0.0 dataset_split: test col_mapping: text: article target: highlights --- # Dataset Card for AutoTrain Evaluator This repository contains model predictions generated by [AutoTrain](https://huggingface.co/autotrain) for the following task and dataset: * Task: Summarization * Model: pszemraj/long-t5-tglobal-base-16384-book-summary * Dataset: cnn_dailymail * Config: 3.0.0 * Split: test To run new evaluation jobs, visit Hugging Face's [automatic model evaluator](https://huggingface.co/spaces/autoevaluate/model-evaluator). ## Contributions Thanks to [@pszemraj](https://huggingface.co/pszemraj) for evaluating this model.
Rodekool
null
null
still a WIP, Dataset originally comes from Open Data van de Rechtspraak"
false
1
false
Rodekool/ornl20
2022-07-15T16:37:42.000Z
null
false
c22d78bd8e5d07995a0ae41708457c47dcbe0bf2
[]
[ "license:gpl" ]
https://huggingface.co/datasets/Rodekool/ornl20/resolve/main/README.md
--- license: gpl ---
nprime496
null
null
null
false
1
false
nprime496/building_floor_classification
2022-09-08T15:12:55.000Z
null
false
c5bc19d940ee20698ebb845bcca4cdb8dca6e488
[]
[]
https://huggingface.co/datasets/nprime496/building_floor_classification/resolve/main/README.md
Dataset_chunked_5 : chunks of 05 seconds obtained from expert samples Dataset_chunked_10 : chunks of 10 seconds obtained from expert samples Dataset_expanded : chunks of 10 seconds obtained from whole samples Data.zip : original dataset
rajistics
null
null
null
false
150
false
rajistics/indian_food_images
2022-08-04T17:58:49.000Z
null
false
7d5c188c0bb71619f3966f8ba8f99df333f04168
[]
[ "task_categories:image-classification" ]
https://huggingface.co/datasets/rajistics/indian_food_images/resolve/main/README.md
--- task_categories: - image-classification --- Source of dataset: [Kaggle](https://www.kaggle.com/datasets/l33tc0d3r/indian-food-classification) This Dataset contains different images of food in 20 different classes. Some of the classes are of Indian food. All the images are extracted from google. Images per classes are little so Data augmentation and transfer learning will be best suited here. Classes of the model: "burger", "butter_naan", "chai", "chapati", "chole_bhature", "dal_makhani", "dhokla", "fried_rice", "idli", "jalebi", "kaathi_rolls", "kadai_paneer", "kulfi", "masala_dosa", "momos", "paani_puri", "pakode", "pav_bhaji", "pizza", "samosa"
autoevaluate
null
null
null
false
1
false
autoevaluate/autoeval-staging-eval-project-samsum-22cb3f56-11055482
2022-07-15T18:48:48.000Z
null
false
e524a8f5fc2bdd5e345a8bb992813952165d21bb
[]
[ "type:predictions", "tags:autotrain", "tags:evaluation", "datasets:samsum" ]
https://huggingface.co/datasets/autoevaluate/autoeval-staging-eval-project-samsum-22cb3f56-11055482/resolve/main/README.md
--- type: predictions tags: - autotrain - evaluation datasets: - samsum eval_info: task: summarization model: pszemraj/led-base-book-summary metrics: [] dataset_name: samsum dataset_config: samsum dataset_split: test col_mapping: text: dialogue target: summary --- # Dataset Card for AutoTrain Evaluator This repository contains model predictions generated by [AutoTrain](https://huggingface.co/autotrain) for the following task and dataset: * Task: Summarization * Model: pszemraj/led-base-book-summary * Dataset: samsum * Config: samsum * Split: test To run new evaluation jobs, visit Hugging Face's [automatic model evaluator](https://huggingface.co/spaces/autoevaluate/model-evaluator). ## Contributions Thanks to [@pszemraj](https://huggingface.co/pszemraj) for evaluating this model.
autoevaluate
null
null
null
false
1
false
autoevaluate/autoeval-staging-eval-project-samsum-07954c9f-11065483
2022-07-15T19:55:26.000Z
null
false
6c07ee98f2e111eee37e96bf47af2bff73032d56
[]
[ "type:predictions", "tags:autotrain", "tags:evaluation", "datasets:samsum" ]
https://huggingface.co/datasets/autoevaluate/autoeval-staging-eval-project-samsum-07954c9f-11065483/resolve/main/README.md
--- type: predictions tags: - autotrain - evaluation datasets: - samsum eval_info: task: summarization model: pszemraj/led-large-book-summary metrics: [] dataset_name: samsum dataset_config: samsum dataset_split: test col_mapping: text: dialogue target: summary --- # Dataset Card for AutoTrain Evaluator This repository contains model predictions generated by [AutoTrain](https://huggingface.co/autotrain) for the following task and dataset: * Task: Summarization * Model: pszemraj/led-large-book-summary * Dataset: samsum * Config: samsum * Split: test To run new evaluation jobs, visit Hugging Face's [automatic model evaluator](https://huggingface.co/spaces/autoevaluate/model-evaluator). ## Contributions Thanks to [@pszemraj](https://huggingface.co/pszemraj) for evaluating this model.
autoevaluate
null
null
null
false
1
false
autoevaluate/autoeval-staging-eval-project-kmfoda__booksum-636bebc2-11085484
2022-07-16T05:43:03.000Z
null
false
5ef5ab57eb6f3b1c19493a6b9cc57c78638e6f1d
[]
[ "type:predictions", "tags:autotrain", "tags:evaluation", "datasets:kmfoda/booksum" ]
https://huggingface.co/datasets/autoevaluate/autoeval-staging-eval-project-kmfoda__booksum-636bebc2-11085484/resolve/main/README.md
--- type: predictions tags: - autotrain - evaluation datasets: - kmfoda/booksum eval_info: task: summarization model: pszemraj/long-t5-tglobal-base-16384-book-summary metrics: [] dataset_name: kmfoda/booksum dataset_config: kmfoda--booksum dataset_split: test col_mapping: text: chapter target: summary_text --- # Dataset Card for AutoTrain Evaluator This repository contains model predictions generated by [AutoTrain](https://huggingface.co/autotrain) for the following task and dataset: * Task: Summarization * Model: pszemraj/long-t5-tglobal-base-16384-book-summary * Dataset: kmfoda/booksum * Config: kmfoda--booksum * Split: test To run new evaluation jobs, visit Hugging Face's [automatic model evaluator](https://huggingface.co/spaces/autoevaluate/model-evaluator). ## Contributions Thanks to [@pszemraj](https://huggingface.co/pszemraj) for evaluating this model.
autoevaluate
null
null
null
false
1
false
autoevaluate/autoeval-staging-eval-project-kmfoda__booksum-f6c9ed7c-11095485
2022-07-17T01:12:42.000Z
null
false
1362c265ff02ad01802147e1f33f60e353776404
[]
[ "type:predictions", "tags:autotrain", "tags:evaluation", "datasets:kmfoda/booksum" ]
https://huggingface.co/datasets/autoevaluate/autoeval-staging-eval-project-kmfoda__booksum-f6c9ed7c-11095485/resolve/main/README.md
--- type: predictions tags: - autotrain - evaluation datasets: - kmfoda/booksum eval_info: task: summarization model: pszemraj/long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP metrics: [] dataset_name: kmfoda/booksum dataset_config: kmfoda--booksum dataset_split: test col_mapping: text: chapter target: summary_text --- # Dataset Card for AutoTrain Evaluator This repository contains model predictions generated by [AutoTrain](https://huggingface.co/autotrain) for the following task and dataset: * Task: Summarization * Model: pszemraj/long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP * Dataset: kmfoda/booksum * Config: kmfoda--booksum * Split: test To run new evaluation jobs, visit Hugging Face's [automatic model evaluator](https://huggingface.co/spaces/autoevaluate/model-evaluator). ## Contributions Thanks to [@pszemraj](https://huggingface.co/pszemraj) for evaluating this model.
Pogpotatofarmer
null
null
null
false
1
false
Pogpotatofarmer/memes
2022-07-15T21:11:34.000Z
null
false
0b174eb4c5ea22a11cbd4994499c2258dd0cc2b0
[]
[ "license:cc" ]
https://huggingface.co/datasets/Pogpotatofarmer/memes/resolve/main/README.md
--- license: cc ---
nbroad
null
@article{zhu2021mediasum, title={MediaSum: A Large-scale Media Interview Dataset for Dialogue Summarization}, author={Zhu, Chenguang and Liu, Yang and Mei, Jie and Zeng, Michael}, journal={arXiv preprint arXiv:2103.06410}, year={2021} }
This large-scale media interview dataset contains 463.6K transcripts with abstractive summaries, collected from interview transcripts and overview / topic descriptions from NPR and CNN.
false
13
false
nbroad/mediasum
2022-10-25T10:40:11.000Z
null
false
bcbcef7de3b4e702e526352d825a4ff06de2becb
[]
[ "arxiv:2103.06410", "language:en", "license:cc-by-nc-sa-4.0", "multilinguality:monolingual", "size_categories:100K<n<1M", "task_categories:summarization" ]
https://huggingface.co/datasets/nbroad/mediasum/resolve/main/README.md
--- language: - en license: - cc-by-nc-sa-4.0 multilinguality: - monolingual size_categories: - 100K<n<1M task_categories: - summarization --- # MediaSum ## Description This large-scale media interview dataset contains 463.6K transcripts with abstractive summaries, collected from interview transcripts and overview / topic descriptions from NPR and CNN. ### **NOTE: The authors have requested that this dataset be used for research purposes only** ## Homepage https://github.com/zcgzcgzcg1/MediaSum ## Paper https://arxiv.org/abs/2103.06410 ## Authors ### Chenguang Zhu*, Yang Liu*, Jie Mei, Michael Zeng #### Microsoft Cognitive Services Research Group {chezhu,yaliu10,jimei,nzeng}@microsoft.com ## Citation @article{zhu2021mediasum, title={MediaSum: A Large-scale Media Interview Dataset for Dialogue Summarization}, author={Zhu, Chenguang and Liu, Yang and Mei, Jie and Zeng, Michael}, journal={arXiv preprint arXiv:2103.06410}, year={2021} } ## Dataset size Train: 443,596 Validation: 10,000 Test: 10,000 The splits were made by using the file located here: https://github.com/zcgzcgzcg1/MediaSum/tree/main/data ## Data details - id (string): unique identifier - program (string): the program this transcript came from - date (string): date of program - url (string): link to where audio and transcript are located - title (string): title of the program. some datapoints do not have a title - summary (string): summary of the program - utt (list of string): list of utterances by the speakers in the program. corresponds with `speaker` - speaker (list of string): list of speakers, corresponds with `utt` Example: ``` { "id": "NPR-11", "program": "Day to Day", "date": "2008-06-10", "url": "https://www.npr.org/templates/story/story.php?storyId=91356794", "title": "Researchers Find Discriminating Plants", "summary": "The \"sea rocket\" shows preferential treatment to plants that are its kin. Evolutionary plant ecologist Susan Dudley of McMaster University in Ontario discusses her discovery.", "utt": [ "This is Day to Day. I'm Madeleine Brand.", "And I'm Alex Cohen.", "Coming up, the question of who wrote a famous religious poem turns into a very unchristian battle.", "First, remember the 1970s? People talked to their houseplants, played them classical music. They were convinced plants were sensuous beings and there was that 1979 movie, \"The Secret Life of Plants.\"", "Only a few daring individuals, from the scientific establishment, have come forward with offers to replicate his experiments, or test his results. The great majority are content simply to condemn his efforts without taking the trouble to investigate their validity.", ... "OK. Thank you.", "That's Susan Dudley. She's an associate professor of biology at McMaster University in Hamilt on Ontario. She discovered that there is a social life of plants." ], "speaker": [ "MADELEINE BRAND, host", "ALEX COHEN, host", "ALEX COHEN, host", "MADELEINE BRAND, host", "Unidentified Male", ..." Professor SUSAN DUDLEY (Biology, McMaster University)", "MADELEINE BRAND, host" ] } ``` ## Using the dataset ```python from datasets import load_dataset ds = load_dataset("nbroad/mediasum") ``` ## Data location https://drive.google.com/file/d/1ZAKZM1cGhEw2A4_n4bGGMYyF8iPjLZni/view?usp=sharing ## License No license specified, but the authors have requested that this dataset be used for research purposes only.
hevia
null
null
null
false
1
false
hevia/scp-embeddings
2022-07-15T22:01:22.000Z
null
false
97cfbaf63ee4ea7128b5f7d95ec2af38a2f2f369
[]
[]
https://huggingface.co/datasets/hevia/scp-embeddings/resolve/main/README.md
# SCP Text+ Embeddings This dataset is adapted from the [SCP 1to 7 corpus from Kaggle](https://www.kaggle.com/datasets/czzzzzzz/scp1to7) We concatenated the title, state, text, and image captions columns. We also removed any rows that contained a deleted page, which trims the results down from 6999 -> 6618. The embeddings were generated using [sentence-transformers/multi-qa-mpnet-base-dot-v1](https://huggingface.co/sentence-transformers/multi-qa-mpnet-base-cos-v1) Feel free to use the dataset for semantic search or text generation tasks!
ivv101
null
null
null
false
1
false
ivv101/test_dataset
2022-07-16T00:00:30.000Z
null
false
1bb08f5f5c2479942aa77e567cf6c58e2104cab6
[]
[ "license:cc0-1.0" ]
https://huggingface.co/datasets/ivv101/test_dataset/resolve/main/README.md
--- license: cc0-1.0 ---
oyk100
null
null
null
false
2
false
oyk100/ChaSES-data
2022-07-21T01:55:24.000Z
null
false
14fb2fd3f3e1cf02d60b4bb756ab877f8c410481
[]
[ "license:cc0-1.0" ]
https://huggingface.co/datasets/oyk100/ChaSES-data/resolve/main/README.md
--- license: cc0-1.0 ---
IRVLUTD
null
null
null
false
1
false
IRVLUTD/few-sol
2022-07-16T03:16:24.000Z
null
false
02b0b146ca6f20117bf48e19678536ace6362254
[]
[ "license:mit" ]
https://huggingface.co/datasets/IRVLUTD/few-sol/resolve/main/README.md
--- license: mit ---
tner
null
@inproceedings{tjong-kim-sang-de-meulder-2003-introduction, title = "Introduction to the {C}o{NLL}-2003 Shared Task: Language-Independent Named Entity Recognition", author = "Tjong Kim Sang, Erik F. and De Meulder, Fien", booktitle = "Proceedings of the Seventh Conference on Natural Language Learning at {HLT}-{NAACL} 2003", year = "2003", url = "https://www.aclweb.org/anthology/W03-0419", pages = "142--147", }
[CoNLL 2003 NER dataset](https://aclanthology.org/W03-0419/)
false
173
false
tner/conll2003
2022-07-18T00:43:28.000Z
null
false
b18612dee0007b1f7129731dbf2f5f2ed4039ad3
[]
[ "language:en", "license:other", "multilinguality:monolingual", "size_categories:10K<n<100K", "task_categories:token-classification", "task_ids:named-entity-recognition" ]
https://huggingface.co/datasets/tner/conll2003/resolve/main/README.md
--- language: - en license: - other multilinguality: - monolingual size_categories: - 10K<n<100K task_categories: - token-classification task_ids: - named-entity-recognition pretty_name: CoNLL-2003 --- # Dataset Card for "tner/conll2003" ## Dataset Description - **Repository:** [T-NER](https://github.com/asahi417/tner) - **Paper:** [https://www.aclweb.org/anthology/W03-0419/](https://www.aclweb.org/anthology/W03-0419/) - **Dataset:** CoNLL 2003 - **Domain:** News - **Number of Entity:** 3 ### Dataset Summary CoNLL-2003 NER dataset formatted in a part of [TNER](https://github.com/asahi417/tner) project. - Entity Types: `ORG`, `PER`, `LOC`, `MISC` ## Dataset Structure ### Data Instances An example of `train` looks as follows. ``` { 'tags': ['SOCCER','-', 'JAPAN', 'GET', 'LUCKY', 'WIN', ',', 'CHINA', 'IN', 'SURPRISE', 'DEFEAT', '.'], 'tokens': [0, 0, 5, 0, 0, 0, 0, 3, 0, 0, 0, 0] } ``` ### Label ID The label2id dictionary can be found at [here](https://huggingface.co/datasets/tner/conll2003/raw/main/dataset/label.json). ```python { "O": 0, "B-ORG": 1, "B-MISC": 2, "B-PER": 3, "I-PER": 4, "B-LOC": 5, "I-ORG": 6, "I-MISC": 7, "I-LOC": 8 } ``` ### Data Splits | name |train|validation|test| |---------|----:|---------:|---:| |conll2003|14041| 3250|3453| ### Licensing Information From the [CoNLL2003 shared task](https://www.clips.uantwerpen.be/conll2003/ner/) page: > The English data is a collection of news wire articles from the Reuters Corpus. The annotation has been done by people of the University of Antwerp. Because of copyright reasons we only make available the annotations. In order to build the complete data sets you will need access to the Reuters Corpus. It can be obtained for research purposes without any charge from NIST. The copyrights are defined below, from the [Reuters Corpus page](https://trec.nist.gov/data/reuters/reuters.html): > The stories in the Reuters Corpus are under the copyright of Reuters Ltd and/or Thomson Reuters, and their use is governed by the following agreements: > > [Organizational agreement](https://trec.nist.gov/data/reuters/org_appl_reuters_v4.html) > > This agreement must be signed by the person responsible for the data at your organization, and sent to NIST. > > [Individual agreement](https://trec.nist.gov/data/reuters/ind_appl_reuters_v4.html) > > This agreement must be signed by all researchers using the Reuters Corpus at your organization, and kept on file at your organization. ### Citation Information ``` @inproceedings{tjong-kim-sang-de-meulder-2003-introduction, title = "Introduction to the {C}o{NLL}-2003 Shared Task: Language-Independent Named Entity Recognition", author = "Tjong Kim Sang, Erik F. and De Meulder, Fien", booktitle = "Proceedings of the Seventh Conference on Natural Language Learning at {HLT}-{NAACL} 2003", year = "2003", url = "https://www.aclweb.org/anthology/W03-0419", pages = "142--147", } ```
tner
null
@inproceedings{hovy-etal-2006-ontonotes, title = "{O}nto{N}otes: The 90{\%} Solution", author = "Hovy, Eduard and Marcus, Mitchell and Palmer, Martha and Ramshaw, Lance and Weischedel, Ralph", booktitle = "Proceedings of the Human Language Technology Conference of the {NAACL}, Companion Volume: Short Papers", month = jun, year = "2006", address = "New York City, USA", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/N06-2015", pages = "57--60", }
[ontonotes5 NER dataset](https://aclanthology.org/N06-2015/)
false
567
false
tner/ontonotes5
2022-07-18T00:43:55.000Z
null
false
cf9ef57ad260810be1298ba795d83c09a915e959
[]
[ "language:en", "license:other", "multilinguality:monolingual", "size_categories:10K<n<100K", "task_categories:token-classification", "task_ids:named-entity-recognition" ]
https://huggingface.co/datasets/tner/ontonotes5/resolve/main/README.md
--- language: - en license: - other multilinguality: - monolingual size_categories: - 10K<n<100K task_categories: - token-classification task_ids: - named-entity-recognition pretty_name: Ontonotes5 --- # Dataset Card for "tner/ontonotes5" ## Dataset Description - **Repository:** [T-NER](https://github.com/asahi417/tner) - **Paper:** [https://aclanthology.org/N06-2015/](https://aclanthology.org/N06-2015/) - **Dataset:** Ontonotes5 - **Domain:** News - **Number of Entity:** 8 ### Dataset Summary Ontonotes5 NER dataset formatted in a part of [TNER](https://github.com/asahi417/tner) project. - Entity Types: `CARDINAL`, `DATE`, `PERSON`, `NORP`, `GPE`, `LAW`, `PERCENT`, `ORDINAL`, `MONEY`, `WORK_OF_ART`, `FAC`, `TIME`, `QUANTITY`, `PRODUCT`, `LANGUAGE`, `ORG`, `LOC`, `EVENT` ## Dataset Structure ### Data Instances An example of `train` looks as follows. ``` { 'tags': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 4, 5, 0, 0, 0, 0, 11, 12, 12, 12, 12, 0, 0, 7, 0, 0, 0, 0, 0], 'tokens': ['``', 'It', "'s", 'very', 'costly', 'and', 'time', '-', 'consuming', ',', "''", 'says', 'Phil', 'Rosen', ',', 'a', 'partner', 'in', 'Fleet', '&', 'Leasing', 'Management', 'Inc.', ',', 'a', 'Boston', 'car', '-', 'leasing', 'company', '.'] } ``` ### Label ID The label2id dictionary can be found at [here](https://huggingface.co/datasets/tner/onotonotes5/raw/main/dataset/label.json). ```python { "O": 0, "B-CARDINAL": 1, "B-DATE": 2, "I-DATE": 3, "B-PERSON": 4, "I-PERSON": 5, "B-NORP": 6, "B-GPE": 7, "I-GPE": 8, "B-LAW": 9, "I-LAW": 10, "B-ORG": 11, "I-ORG": 12, "B-PERCENT": 13, "I-PERCENT": 14, "B-ORDINAL": 15, "B-MONEY": 16, "I-MONEY": 17, "B-WORK_OF_ART": 18, "I-WORK_OF_ART": 19, "B-FAC": 20, "B-TIME": 21, "I-CARDINAL": 22, "B-LOC": 23, "B-QUANTITY": 24, "I-QUANTITY": 25, "I-NORP": 26, "I-LOC": 27, "B-PRODUCT": 28, "I-TIME": 29, "B-EVENT": 30, "I-EVENT": 31, "I-FAC": 32, "B-LANGUAGE": 33, "I-PRODUCT": 34, "I-ORDINAL": 35, "I-LANGUAGE": 36 } ``` ### Data Splits | name |train|validation|test| |---------|----:|---------:|---:| |ontonotes5|59924| 8528|8262| ### Citation Information ``` @inproceedings{hovy-etal-2006-ontonotes, title = "{O}nto{N}otes: The 90{\%} Solution", author = "Hovy, Eduard and Marcus, Mitchell and Palmer, Martha and Ramshaw, Lance and Weischedel, Ralph", booktitle = "Proceedings of the Human Language Technology Conference of the {NAACL}, Companion Volume: Short Papers", month = jun, year = "2006", address = "New York City, USA", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/N06-2015", pages = "57--60", } ```
tner
null
@inproceedings{derczynski-etal-2017-results, title = "Results of the {WNUT}2017 Shared Task on Novel and Emerging Entity Recognition", author = "Derczynski, Leon and Nichols, Eric and van Erp, Marieke and Limsopatham, Nut", booktitle = "Proceedings of the 3rd Workshop on Noisy User-generated Text", month = sep, year = "2017", address = "Copenhagen, Denmark", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/W17-4418", doi = "10.18653/v1/W17-4418", pages = "140--147", abstract = "This shared task focuses on identifying unusual, previously-unseen entities in the context of emerging discussions. Named entities form the basis of many modern approaches to other tasks (like event clustering and summarization), but recall on them is a real problem in noisy text - even among annotators. This drop tends to be due to novel entities and surface forms. Take for example the tweet {``}so.. kktny in 30 mins?!{''} {--} even human experts find the entity {`}kktny{'} hard to detect and resolve. The goal of this task is to provide a definition of emerging and of rare entities, and based on that, also datasets for detecting these entities. The task as described in this paper evaluated the ability of participating entries to detect and classify novel and emerging named entities in noisy text.", }
[WNUT 2017 NER dataset](https://aclanthology.org/W17-4418/)
false
375
false
tner/wnut2017
2022-08-06T23:30:30.000Z
null
false
068c8163eee17ea24bdc86211efeaa9001b57c33
[]
[ "language:en", "license:other", "multilinguality:monolingual", "size_categories:1k<10K", "task_categories:token-classification", "task_ids:named-entity-recognition" ]
https://huggingface.co/datasets/tner/wnut2017/resolve/main/README.md
--- language: - en license: - other multilinguality: - monolingual size_categories: - 1k<10K task_categories: - token-classification task_ids: - named-entity-recognition pretty_name: WNUT 2017 --- # Dataset Card for "tner/wnut2017" ## Dataset Description - **Repository:** [T-NER](https://github.com/asahi417/tner) - **Paper:** [https://aclanthology.org/W17-4418/](https://aclanthology.org/W17-4418/) - **Dataset:** WNUT 2017 - **Domain:** Twitter, Reddit, YouTube, and StackExchange - **Number of Entity:** 6 ### Dataset Summary WNUT 2017 NER dataset formatted in a part of [TNER](https://github.com/asahi417/tner) project. - Entity Types: `creative-work`, `corporation`, `group`, `location`, `person`, `product` ## Dataset Structure ### Data Instances An example of `train` looks as follows. ``` { 'tokens': ['@paulwalk', 'It', "'s", 'the', 'view', 'from', 'where', 'I', "'m", 'living', 'for', 'two', 'weeks', '.', 'Empire', 'State', 'Building', '=', 'ESB', '.', 'Pretty', 'bad', 'storm', 'here', 'last', 'evening', '.'], 'tags': [12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 3, 9, 9, 12, 3, 12, 12, 12, 12, 12, 12, 12, 12] } ``` ### Label ID The label2id dictionary can be found at [here](https://huggingface.co/datasets/tner/wnut2017/raw/main/dataset/label.json). ```python { "B-corporation": 0, "B-creative-work": 1, "B-group": 2, "B-location": 3, "B-person": 4, "B-product": 5, "I-corporation": 6, "I-creative-work": 7, "I-group": 8, "I-location": 9, "I-person": 10, "I-product": 11, "O": 12 } ``` ### Data Splits | name |train|validation|test| |---------|----:|---------:|---:| |wnut2017 | 2395| 1009|1287| ### Citation Information ``` @inproceedings{derczynski-etal-2017-results, title = "Results of the {WNUT}2017 Shared Task on Novel and Emerging Entity Recognition", author = "Derczynski, Leon and Nichols, Eric and van Erp, Marieke and Limsopatham, Nut", booktitle = "Proceedings of the 3rd Workshop on Noisy User-generated Text", month = sep, year = "2017", address = "Copenhagen, Denmark", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/W17-4418", doi = "10.18653/v1/W17-4418", pages = "140--147", abstract = "This shared task focuses on identifying unusual, previously-unseen entities in the context of emerging discussions. Named entities form the basis of many modern approaches to other tasks (like event clustering and summarization), but recall on them is a real problem in noisy text - even among annotators. This drop tends to be due to novel entities and surface forms. Take for example the tweet {``}so.. kktny in 30 mins?!{''} {--} even human experts find the entity {`}kktny{'} hard to detect and resolve. The goal of this task is to provide a definition of emerging and of rare entities, and based on that, also datasets for detecting these entities. The task as described in this paper evaluated the ability of participating entries to detect and classify novel and emerging named entities in noisy text.", } ```
tner
null
@inproceedings{salinas-alvarado-etal-2015-domain, title = "Domain Adaption of Named Entity Recognition to Support Credit Risk Assessment", author = "Salinas Alvarado, Julio Cesar and Verspoor, Karin and Baldwin, Timothy", booktitle = "Proceedings of the Australasian Language Technology Association Workshop 2015", month = dec, year = "2015", address = "Parramatta, Australia", url = "https://aclanthology.org/U15-1010", pages = "84--90", }
[FIN NER dataset](https://aclanthology.org/U15-1010.pdf)
false
337
false
tner/fin
2022-08-15T17:50:31.000Z
null
false
e79eb66d7f3ee016c31e70ad9d48e33f15047786
[]
[ "language:en", "license:mit", "multilinguality:monolingual", "size_categories:1K<n<10K", "task_categories:token-classification", "task_ids:named-entity-recognition" ]
https://huggingface.co/datasets/tner/fin/resolve/main/README.md
--- language: - en license: - mit multilinguality: - monolingual size_categories: - 1K<n<10K task_categories: - token-classification task_ids: - named-entity-recognition pretty_name: FIN --- # Dataset Card for "tner/fin" ## Dataset Description - **Repository:** [T-NER](https://github.com/asahi417/tner) - **Paper:** [https://aclanthology.org/U15-1010.pdf](https://aclanthology.org/U15-1010.pdf) - **Dataset:** FIN - **Domain:** Financial News - **Number of Entity:** 4 ### Dataset Summary FIN NER dataset formatted in a part of [TNER](https://github.com/asahi417/tner) project. FIN dataset contains training (FIN5) and test (FIN3) only, so we randomly sample a half size of test instances from the training set to create validation set. - Entity Types: `ORG`, `LOC`, `PER`, `MISC` ## Dataset Structure ### Data Instances An example of `train` looks as follows. ``` { "tags": [0, 0, 0, 0, 0, 3, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], "tokens": ["1", ".", "1", ".", "4", "Borrower", "engages", "in", "criminal", "conduct", "or", "is", "involved", "in", "criminal", "activities", ";"] } ``` ### Label ID The label2id dictionary can be found at [here](https://huggingface.co/datasets/tner/fin/raw/main/dataset/label.json). ```python { "O": 0, "B-PER": 1, "B-LOC": 2, "B-ORG": 3, "B-MISC": 4, "I-PER": 5, "I-LOC": 6, "I-ORG": 7, "I-MISC": 8 } ``` ### Data Splits | name |train|validation|test| |---------|----:|---------:|---:| |fin |1014 | 303| 150| ### Citation Information ``` @inproceedings{salinas-alvarado-etal-2015-domain, title = "Domain Adaption of Named Entity Recognition to Support Credit Risk Assessment", author = "Salinas Alvarado, Julio Cesar and Verspoor, Karin and Baldwin, Timothy", booktitle = "Proceedings of the Australasian Language Technology Association Workshop 2015", month = dec, year = "2015", address = "Parramatta, Australia", url = "https://aclanthology.org/U15-1010", pages = "84--90", } ```
tner
null
@inproceedings{collier-kim-2004-introduction, title = "Introduction to the Bio-entity Recognition Task at {JNLPBA}", author = "Collier, Nigel and Kim, Jin-Dong", booktitle = "Proceedings of the International Joint Workshop on Natural Language Processing in Biomedicine and its Applications ({NLPBA}/{B}io{NLP})", month = aug # " 28th and 29th", year = "2004", address = "Geneva, Switzerland", publisher = "COLING", url = "https://aclanthology.org/W04-1213", pages = "73--78", }
[BioNLP2004 NER dataset](https://aclanthology.org/W04-1213.pdf)
false
119
false
tner/bionlp2004
2022-08-10T01:01:51.000Z
null
false
8d75081cb3dae70b3f59db7e8d851dbc42f9275d
[]
[ "language:en", "license:other", "multilinguality:monolingual", "size_categories:10K<n<100K", "task_categories:token-classification", "task_ids:named-entity-recognition" ]
https://huggingface.co/datasets/tner/bionlp2004/resolve/main/README.md
--- language: - en license: - other multilinguality: - monolingual size_categories: - 10K<n<100K task_categories: - token-classification task_ids: - named-entity-recognition pretty_name: BioNLP2004 --- # Dataset Card for "tner/bionlp2004" ## Dataset Description - **Repository:** [T-NER](https://github.com/asahi417/tner) - **Paper:** [https://aclanthology.org/U15-1010.pdf](https://aclanthology.org/U15-1010.pdf) - **Dataset:** BioNLP2004 - **Domain:** Biochemical - **Number of Entity:** 5 ### Dataset Summary BioNLP2004 NER dataset formatted in a part of [TNER](https://github.com/asahi417/tner) project. BioNLP2004 dataset contains training and test only, so we randomly sample a half size of test instances from the training set to create validation set. - Entity Types: `DNA`, `protein`, `cell_type`, `cell_line`, `RNA` ## Dataset Structure ### Data Instances An example of `train` looks as follows. ``` { 'tags': [0, 0, 0, 0, 3, 0, 9, 10, 0, 0, 0, 0, 0, 7, 8, 0, 3, 0, 0, 9, 10, 10, 0, 0], 'tokens': ['In', 'the', 'presence', 'of', 'Epo', ',', 'c-myb', 'mRNA', 'declined', 'and', '20', '%', 'of', 'K562', 'cells', 'synthesized', 'Hb', 'regardless', 'of', 'antisense', 'myb', 'RNA', 'expression', '.'] } ``` ### Label ID The label2id dictionary can be found at [here](https://huggingface.co/datasets/tner/fin/raw/main/dataset/label.json). ```python { "O": 0, "B-DNA": 1, "I-DNA": 2, "B-protein": 3, "I-protein": 4, "B-cell_type": 5, "I-cell_type": 6, "B-cell_line": 7, "I-cell_line": 8, "B-RNA": 9, "I-RNA": 10 } ``` ### Data Splits | name |train|validation|test| |---------|----:|---------:|---:| |bionlp2004 |16619 | 1927| 3856| ### Citation Information ``` @inproceedings{collier-kim-2004-introduction, title = "Introduction to the Bio-entity Recognition Task at {JNLPBA}", author = "Collier, Nigel and Kim, Jin-Dong", booktitle = "Proceedings of the International Joint Workshop on Natural Language Processing in Biomedicine and its Applications ({NLPBA}/{B}io{NLP})", month = aug # " 28th and 29th", year = "2004", address = "Geneva, Switzerland", publisher = "COLING", url = "https://aclanthology.org/W04-1213", pages = "73--78", } ```
tner
null
@article{wei2016assessing, title={Assessing the state of the art in biomedical relation extraction: overview of the BioCreative V chemical-disease relation (CDR) task}, author={Wei, Chih-Hsuan and Peng, Yifan and Leaman, Robert and Davis, Allan Peter and Mattingly, Carolyn J and Li, Jiao and Wiegers, Thomas C and Lu, Zhiyong}, journal={Database}, volume={2016}, year={2016}, publisher={Oxford Academic} }
[Bio Creative 5 CDR NER dataset](https://academic.oup.com/database/article/doi/10.1093/database/baw032/2630271?login=true)
false
178
false
tner/bc5cdr
2022-07-18T00:43:04.000Z
null
false
f68cdc7db924369241e7868656f583072acd4e90
[]
[ "language:en", "license:other", "multilinguality:monolingual", "size_categories:10K<n<100K", "task_categories:token-classification", "task_ids:named-entity-recognition" ]
https://huggingface.co/datasets/tner/bc5cdr/resolve/main/README.md
--- language: - en license: - other multilinguality: - monolingual size_categories: - 10K<n<100K task_categories: - token-classification task_ids: - named-entity-recognition pretty_name: BioCreative V CDR --- # Dataset Card for "tner/bc5cdr" ## Dataset Description - **Repository:** [T-NER](https://github.com/asahi417/tner) - **Paper:** [https://academic.oup.com/database/article/doi/10.1093/database/baw032/2630271?login=true](https://academic.oup.com/database/article/doi/10.1093/database/baw032/2630271?login=true) - **Dataset:** BioCreative V CDR - **Domain:** Biomedical - **Number of Entity:** 2 ### Dataset Summary BioCreative V CDR NER dataset formatted in a part of [TNER](https://github.com/asahi417/tner) project. The original dataset consists of long documents which cannot be fed on LM because of the length, so we split them into sentences to reduce their size. - Entity Types: `Chemical`, `Disease` ## Dataset Structure ### Data Instances An example of `train` looks as follows. ``` { 'tags': [2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2, 0, 0], 'tokens': ['Fasciculations', 'in', 'six', 'areas', 'of', 'the', 'body', 'were', 'scored', 'from', '0', 'to', '3', 'and', 'summated', 'as', 'a', 'total', 'fasciculation', 'score', '.'] } ``` ### Label ID The label2id dictionary can be found at [here](https://huggingface.co/datasets/tner/bc5cdr/raw/main/dataset/label.json). ```python { "O": 0, "B-Chemical": 1, "B-Disease": 2, "I-Disease": 3, "I-Chemical": 4 } ``` ### Data Splits | name |train|validation|test| |---------|----:|---------:|---:| |bc5cdr|5228| 5330|5865| ### Citation Information ``` @article{wei2016assessing, title={Assessing the state of the art in biomedical relation extraction: overview of the BioCreative V chemical-disease relation (CDR) task}, author={Wei, Chih-Hsuan and Peng, Yifan and Leaman, Robert and Davis, Allan Peter and Mattingly, Carolyn J and Li, Jiao and Wiegers, Thomas C and Lu, Zhiyong}, journal={Database}, volume={2016}, year={2016}, publisher={Oxford Academic} } ```
tner
null
null
MIT Movie
false
153
false
tner/mit_movie_trivia
2022-07-18T10:24:52.000Z
null
false
d35f3cd11c9c5c1754ef66bfcbcb6a8e632216a6
[]
[ "language:en", "license:other", "multilinguality:monolingual", "size_categories:1K<n<10K", "task_categories:token-classification", "task_ids:named-entity-recognition" ]
https://huggingface.co/datasets/tner/mit_movie_trivia/resolve/main/README.md
--- language: - en license: - other multilinguality: - monolingual size_categories: - 1K<n<10K task_categories: - token-classification task_ids: - named-entity-recognition pretty_name: MIT Movie --- # Dataset Card for "tner/mit_movie_trivia" ## Dataset Description - **Repository:** [T-NER](https://github.com/asahi417/tner) - **Dataset:** MIT Movie - **Domain:** Movie - **Number of Entity:** 12 ### Dataset Summary MIT Movie NER dataset formatted in a part of [TNER](https://github.com/asahi417/tner) project. - Entity Types: `Actor`, `Plot`, `Opinion`, `Award`, `Year`, `Genre`, `Origin`, `Director`, `Soundtrack`, `Relationship`, `Character_Name`, `Quote` ## Dataset Structure ### Data Instances An example of `train` looks as follows. ``` { 'tags': [0, 13, 14, 0, 0, 0, 3, 4, 4, 4, 4, 4, 4, 4, 4], 'tokens': ['a', 'steven', 'spielberg', 'film', 'featuring', 'a', 'bluff', 'called', 'devil', 's', 'tower', 'and', 'a', 'spectacular', 'mothership'] } ``` ### Label ID The label2id dictionary can be found at [here](https://huggingface.co/datasets/tner/mit_movie_trivia/raw/main/dataset/label.json). ```python { "O": 0, "B-Actor": 1, "I-Actor": 2, "B-Plot": 3, "I-Plot": 4, "B-Opinion": 5, "I-Opinion": 6, "B-Award": 7, "I-Award": 8, "B-Year": 9, "B-Genre": 10, "B-Origin": 11, "I-Origin": 12, "B-Director": 13, "I-Director": 14, "I-Genre": 15, "I-Year": 16, "B-Soundtrack": 17, "I-Soundtrack": 18, "B-Relationship": 19, "I-Relationship": 20, "B-Character_Name": 21, "I-Character_Name": 22, "B-Quote": 23, "I-Quote": 24 } ``` ### Data Splits | name |train|validation|test| |---------|----:|---------:|---:| |mit_movie_trivia |6816 | 1000| 1953|
tner
null
null
[mit_restaurant NER dataset](https://groups.csail.mit.edu/sls/downloads/)
false
312
false
tner/mit_restaurant
2022-08-10T11:25:17.000Z
null
false
538663410a86a70f788b0c193d42320de330cc0d
[]
[ "language:en", "license:other", "multilinguality:monolingual", "size_categories:1K<n<10K", "task_categories:token-classification", "task_ids:named-entity-recognition" ]
https://huggingface.co/datasets/tner/mit_restaurant/resolve/main/README.md
--- language: - en license: - other multilinguality: - monolingual size_categories: - 1K<n<10K task_categories: - token-classification task_ids: - named-entity-recognition pretty_name: MIT Restaurant --- # Dataset Card for "tner/mit_restaurant" ## Dataset Description - **Repository:** [T-NER](https://github.com/asahi417/tner) - **Dataset:** MIT restaurant - **Domain:** Restaurant - **Number of Entity:** 8 ### Dataset Summary MIT Restaurant NER dataset formatted in a part of [TNER](https://github.com/asahi417/tner) project. - Entity Types: `Rating`, `Amenity`, `Location`, `Restaurant_Name`, `Price`, `Hours`, `Dish`, `Cuisine`. ## Dataset Structure ### Data Instances An example of `train` looks as follows. ``` { 'tags': [0, 0, 0, 0, 0, 0, 0, 0, 5, 3, 4, 0], 'tokens': ['can', 'you', 'find', 'the', 'phone', 'number', 'for', 'the', 'closest', 'family', 'style', 'restaurant'] } ``` ### Label ID The label2id dictionary can be found at [here](https://huggingface.co/datasets/tner/mit_restaurant/raw/main/dataset/label.json). ```python { "O": 0, "B-Rating": 1, "I-Rating": 2, "B-Amenity": 3, "I-Amenity": 4, "B-Location": 5, "I-Location": 6, "B-Restaurant_Name": 7, "I-Restaurant_Name": 8, "B-Price": 9, "B-Hours": 10, "I-Hours": 11, "B-Dish": 12, "I-Dish": 13, "B-Cuisine": 14, "I-Price": 15, "I-Cuisine": 16 } ``` ### Data Splits | name |train|validation|test| |---------|----:|---------:|---:| |mit_restaurant |6900 | 760| 1521|
spy24
null
null
null
false
1
false
spy24/Lie_Detection
2022-07-16T12:12:02.000Z
null
false
6a4318523b3f89dc8cadde67a48397563d8e6c7e
[]
[]
https://huggingface.co/datasets/spy24/Lie_Detection/resolve/main/README.md
Chamroush
null
null
null
false
1
false
Chamroush/Exclusive
2022-07-16T14:25:35.000Z
null
false
aa16462095062503b338cff04757d6cfe7ff1194
[]
[ "license:artistic-2.0" ]
https://huggingface.co/datasets/Chamroush/Exclusive/resolve/main/README.md
--- license: artistic-2.0 ---
Blaise-g
null
null
null
false
1
false
Blaise-g/SumPubmed
2022-07-28T19:53:40.000Z
null
false
e1e1c9c6df62fc24117639ec35e02e06abb9c493
[]
[ "language:en" ]
https://huggingface.co/datasets/Blaise-g/SumPubmed/resolve/main/README.md
--- language: - en paperswithcode_id: pretty_name: SumPubmed train-eval-index: - config: Blaise-g--SumPubmed task: summarization task_id: summarization splits: eval_split: test col_mapping: text: text abstract: target --- # Dataset Card for "SumPubmed" ## Original Dataset Description - **Repository:** [https://github.com/vgupta123/sumpubmed](https://github.com/vgupta123/sumpubmed) - **Paper:** [More Information Needed](https://vgupta123.github.io/docs/121_paper.pdf) ## Description of dataset processing 5 rows were dropped from the original dataset taken from KAGGLE as they were missing the respective 'shorter_abstract' entries. The 'line_text' and 'filename_text' columns were left untouched while the remaining ones were processed to remove the '\n' (many repetitions of those present in the original dataset), '\<dig\>', '\<cit\>', 'BACKGROUND', 'RESULTS' and 'CONCLUSIONS' matching strings which were deemed not necessary for the purpose of summarization. Additionally, extra spaces were removed and spacing around punctuations was fixed.
fabiochiu
null
null
null
false
22
false
fabiochiu/medium-articles
2022-07-17T15:17:09.000Z
null
false
979af3bcd84565e3f47b9eca752d8ec112824953
[]
[ "license:mit" ]
https://huggingface.co/datasets/fabiochiu/medium-articles/resolve/main/README.md
--- license: mit --- # Data source This data has been collected through a standard scraping process from the [Medium website](https://medium.com/), looking for published articles. # Data description Each row in the data is a different article published on Medium. For each article, you have the following features: - **title** *[string]*: The title of the article. - **text** *[string]*: The text content of the article. - **url** *[string]*: The URL associated to the article. - **authors** *[list of strings]*: The article authors. - **timestamp** *[string]*: The publication datetime of the article. - **tags** *[list of strings]*: List of tags associated to the article. # Data analysis You can find a very quick data analysis in this [notebook](https://www.kaggle.com/code/fabiochiusano/medium-articles-simple-data-analysis). # What can I do with this data? - A multilabel classification model that assigns tags to articles. - A seq2seq model that generates article titles. - Text analysis. - Finetune text generation models on the general domain of Medium, or on specific domains by filtering articles by the appropriate tags. # Collection methodology Scraping has been done with Python and the requests library. Starting from a random article on Medium, the next articles to scrape are selected by visiting: 1. The author archive pages. 2. The publication archive pages (if present). 3. The tags archives (if present). The article HTML pages have been parsed with the [newspaper Python library](https://github.com/codelucas/newspaper). Published articles have been filtered for English articles only, using the Python [langdetect library](https://pypi.org/project/langdetect/). As a consequence of the collection methodology, the scraped articles are coming from a not uniform publication date distribution. This means that there are articles published in 2016 and in 2022, but the number of articles in this dataset published in 2016 is not the same as the number of articles published in 2022. In particular, there is a strong prevalence of articles published in 2020. Have a look at the [accompanying notebook](https://www.kaggle.com/code/fabiochiusano/medium-articles-simple-data-analysis) to see the distribution of the publication dates.
pnr-svc
null
----Turkish Multiclass Dataset----
The dataset, prepared in Turkish, includes 10.000 tests, 10.000 validations and 33000 train data. The data is composed of customer comments and created from e-commerce sites.
false
2
false
pnr-svc/Turkish-Multiclass-Dataset
2022-07-20T21:40:17.000Z
null
false
c7121ba337f598f3129ebb234d5c95b4fee4d57c
[]
[ "annotations_creators:expert-generated", "language_creators:expert-generated", "language:tr", "license:other", "multilinguality:monolingual", "size_categories:10K<n<100K", "source_datasets:original", "task_categories:text-classification", "task_ids:multi-class-classification", "task_ids:multi-labe...
https://huggingface.co/datasets/pnr-svc/Turkish-Multiclass-Dataset/resolve/main/README.md
--- annotations_creators: - expert-generated language_creators: - expert-generated language: - tr license: - other multilinguality: - monolingual size_categories: - 10K<n<100K source_datasets: - original task_categories: - text-classification task_ids: - multi-class-classification - multi-label-classification pretty_name: 'Turkish-Multiclass-Dataset' train-eval-index: - config: TurkishMulticlassDataset task: text-classification task_id: multi_class_classification splits: eval_split: test col_mapping: text: text label: target --- # Dataset Card for "Turkish-Multiclass-Dataset" ## Table of Contents - [Table of Contents](#table-of-contents) - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Dataset Preprocessing](#dataset-preprocessing) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - **Homepage:** [https://github.com/PnrSvc/Turkish-Multiclass-Dataset] - **Repository:**[https://github.com/PnrSvc/Turkish-Multiclass-Dataset] - **Size of downloaded dataset files:** - **Size of the generated dataset:** ### Dataset Summary The dataset was compiled from user comments from e-commerce sites. It consists of 53,000 validations, 53,000 tests and 160600 train data. Data were classified into 3 classes (positive(pos), negative(neg) and natural(nor). The data is available to you on github. ### Supported Tasks and Leaderboards [More Information Needed] ### Languages [More Information Needed] ## Dataset Structure ### Data Instances [More Information Needed] #### turkish-dataset-v1 - **Size of downloaded dataset files:** - **Size of the generated dataset:** ### Data Fields The data fields are the same among all splits. #### turkish-dataset-v-v1 - `text`: a `string` feature. - `label`: a classification label, with possible values including `positive` (2), `natural` (1), `negative` (0). ### Data Splits | |train |validation|test | |----|--------:|---------:|---------:| |Data| 15000 | 5000| 5000| ## Dataset Creation ### Curation Rationale [More Information Needed] ### Source Data #### Initial Data Collection and Normalization [More Information Needed] #### Who are the source language producers? [More Information Needed] ### Annotations #### Annotation process [More Information Needed] #### Who are the annotators? [More Information Needed] ### Personal and Sensitive Information [More Information Needed] ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed] ### Discussion of Biases [More Information Needed] ### Other Known Limitations [More Information Needed] ## Additional Information ### Dataset Curators [More Information Needed] ### Licensing Information [More Information Needed] ### Citation Information [More Information Needed] ### Contributions Thanks to for adding this dataset.
jvanz
null
null
null
false
52
false
jvanz/portuguese_sentiment_analysis
2022-09-05T20:23:58.000Z
null
false
716b0ac78c49c4bfb32b449dbd394397fc0f0d69
[]
[]
https://huggingface.co/datasets/jvanz/portuguese_sentiment_analysis/resolve/main/README.md
This dataset is based on the dataset originally posted in [Kaggle](https://www.kaggle.com/datasets/fredericods/ptbr-sentiment-analysis-datasets?resource=download)
biglam
null
@article{Howard2017, author = "Sharon Howard", title = "{Old Bailey Online XML Data}", year = "2017", month = "4", url = "https://figshare.shef.ac.uk/articles/dataset/Old_Bailey_Online_XML_Data/4775434", doi = "10.15131/shef.data.4775434.v2" }
The dataset consists of 2,163 transcriptions of the Proceedings and 475 Ordinary's Accounts marked up in TEI-XML, and contains some documentation covering the data structure and variables. Each Proceedings file represents one session of the court (1674-1913), and each Ordinary's Account file represents a single pamphlet (1676-1772)
false
1
false
biglam/old_bailey_proceedings
2022-07-22T17:26:53.000Z
null
false
07f93524c4ac1c70e18a1d67334b7b068e97ec22
[]
[ "annotations_creators:expert-generated", "language:en", "language_creators:expert-generated", "language_creators:machine-generated", "license:cc-by-4.0", "multilinguality:monolingual", "size_categories:1K<n<10K", "source_datasets:original", "task_categories:text-classification", "task_categories:t...
https://huggingface.co/datasets/biglam/old_bailey_proceedings/resolve/main/README.md
--- annotations_creators: - expert-generated language: - en language_creators: - expert-generated - machine-generated license: - cc-by-4.0 multilinguality: - monolingual pretty_name: Old Bailey Proceedings size_categories: - 1K<n<10K source_datasets: - original task_categories: - text-classification - text-generation task_ids: - multi-class-classification - language-modeling - masked-language-modeling --- [Needs More Information] # Dataset Card for Old Bailey Proceedings ## Table of Contents - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-instances) - [Data Splits](#data-instances) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) ## Dataset Description - **Homepage:** https://www.dhi.ac.uk/projects/old-bailey/ - **Repository:** https://www.dhi.ac.uk/san/data/oldbailey/ - **Paper:** [Needs More Information] - **Leaderboard:** [Needs More Information] - **Point of Contact:** The University of Sheffield Digital Humanities Institute 34 Gell Street Sheffield S3 7QY ### Dataset Summary **Note** We are making this dataset available via the HuggingFace hub to open it up to more users and use cases. We have focused primarily on making an initial version of this dataset available, focusing on some potential use cases. If you think there are other configurations this dataset should support, please use the community tab to open an issue. The dataset consists of 2,163 transcriptions of the Proceedings and 475 Ordinary's Accounts marked up in TEI-XML, and contains some documentation covering the data structure and variables. Each Proceedings file represents one session of the court (1674-1913), and each Ordinary's Account file represents a single pamphlet (1676-1772). ### Supported Tasks and Leaderboards - `language-modeling`: This dataset can be used to contribute to the training or evaluation of language models for historical texts. Since it represents transcription from court proceedings, the language in this dataset may better represent the variety of language used at the time. - `text-classification`: This dataset can be used to classify what style of English some text is in - `named-entity-recognition`: Some of the text contains names of people and places. We don't currently provide the token IDs for these entities but do provide the tokens themselves. This means this dataset has the potential to be used to evaluate the performance of other Named Entity Recognition models on this dataset. ### Languages `en` ## Dataset Structure ### Data Instances An example of one instance from the dataset: ```python { 'id': 'OA16760517', 'text': "THE CONFESSION AND EXECUTION Of the Prisoners at TYBURN On Wednesday the 17May1676. Viz. Henry Seabrook , Elizabeth Longman Robert Scot , Condemned the former Sessions. Edward Wall , and Edward Russell . Giving a full and satisfactory Account of their Crimes, Behaviours, Discourses in Prison, and last Words (as neer as could be taken) at the place of Execution. Published for a Warning, to all that read it, to avoid the like wicked Courses, which brought these poor people to this shameful End. THE CONFESSION AND EXECUTION Of the Prisoners at TYBURN On Wednesday the 17th of May, 1676. Viz. Henry Seabrook , Elizabeth Longman Robert Scot , Condemned the former Sessions. Edward Wall , and Edward Russell . Giving a full and satisfactory Account of their Crimes, Behaviours, Discourses in Prison, and last Words (as neer as could be taken) at the place of Execution. Published for a Warning, to all that read it, to avoid the like wicked Courses, which brought these poor people to this shameful End. However, Mercy so far interposed after the Sentence of Justice, that only Five of them actually suffered: Amongst whom was Elizabeth Longman , an old Offendor, having been above a Dozen several times in Newgate : Some time since she was convicted, and obtained the benefit and favour of Transportation, and was accordingly carried into Virginia : But Clum, non Animutant, qu: trans mare currunt. She had not been there above Fourteen Moneths, before she procured Monies remitted from some of the Brotherhood here, wherewith she bought off her Servitude, and ever she comes again into England , long before the term of her Sentence was expired. Nor was she content to violate the Law only in that point, bur returned to her old Trade (for so these people call stealing) as well as to her Countrey; and was soon after her Arrival conducted to Newgate , for mistaking several parcels of Silk, upon which being Convicted, and pleading her Belly, she was set by the last Sessions before this: But now it appearing that she was highly accessary (though all the while in Newgate ) to the Robbery of a Person of Quality, and that she was wholly incorrigible, not to be reclaimed by any Warnings, she was brought down again to the Bar, and demanded, what she could say for her self, why she should not suffer Death, according to Law, upon her old Judgment. To which she still pleaded, that she was quick with Child. But being searched by a Jury of Matrons, they found no such thing; so that she was carried with the rest into the Hole, and ordered for Execution. As for her behaviour, I am sorry no better account can be given of it; for truely she did not seem so sensible of her End, or to make that serious preparation for it, as night be expected from a Person in her condition: yet were not the charitable assistances and endeavours of the Ordinary and several other Ministers wanting towards her, though 'tis feared they did not make the wisht-for Impressions upon her Spirit. Two others viz. Edward Wall and Edward Russel that suffered, were brought to this untimely and ignominious End, by the means and seducements of this unhappy Woman. For they together with one A. M. going after the former Sessions to a Gentlemans House, to sollicite and engage his Interest, in order to the obtaining of a Reprieve for a Woman that past for one of their Wives, and was then under Condemnation, they chanced to spie the Maid a scowring a very considerable quantity of Plate, the glittering sight whereof so much affected them, that when they came back to Newgate , to give an account of their business, amongst other discourse, they mentioned what abundance of Plate they saw. And will you only see it? (says this Besse Longman , being by) then you deserve to starve indeed, when Fortune puts Booty, as it were, in your Mouths, and you are such Cowards, that you dare not take it: With these and many other words to that purpose, she animated them on so far, till by her Instigation and the Devils together, they resolved upon the Villany, and accordingly went the next Night, broke open the Gentlemans House, and took thence a great quantity of Plate: But upon description and search, A. M: was taken next Morning on saffron-hill , with a Silver Ladle, a Silver Porringer, and that famous Engine of Wickedness, called Betty. He was carried for the present to New prison , and there kept till he had discovered the othe. Parties; and upon his ingenu u Confession obtained the Mercy of a Repeve from that Execution, which his Fellow Criminals now suffer'd. The other person executed, was Henry Sea brooke : He was condemned the former Sessions for robbing the Merchant at Dukes Place ; but upon his pretending to discover the rest of the Cabal, and other great matters, was kept from the Gibbet all this, while; but now failing to verifie those pretentions, he was ordered by the Court to receive his punishment according to his former Sentence, with the resof the Prisoners condemned this Sessions. Of these poor wretches, two, viz Wall and Russell, as they ingenuously pleaded guilty to their Indictment at the Bar, so they behaved themselves very modestly at their Condemnation; and afterwards in Prison when Ministers' came to visit and discourse with them, in order to their Souls everlasting good, they received them with great expressions of joy and este, attending with much reverence and seeming heed to their Spiritual Instruction, who with most necessary and importunate Exhortations pressed them to a speedy and hearty Repentance, Since it stood them so much in hand, being upon the brink of Eternity, they told them, Their Condition was sad, as being justly sentenced by Men to a temporal Death; but that was infinitely short of being condemned by God, and suffering Eternal Death under the ury of his Wrath: that though it was vin for them to flatter themselves with hopes of onger life in this world, yet there were means est to secure them of Everlasting Life in the ext: and that to such vile sinners as they nd been, it was an unspeakable Mercy, that hey had yet a little space left them, wherein make their peace with Heaven; and what ould the damned Souls, weltring without pe in Eternal Flames, give or do for such a recious opportunity? With such and many her pious Admonitions and Prescriptions did ese Spiritual Physicians endeavour to cure e Ulcers of their Souls, and excite them to row off the peccant matter, and wash away i Iniquities with tears of a sincere Repennce, proceeding not from a sense of approa- ching Punishment, but of trouble for the Evil itself, and their provoking of God thereby. To all which they gave very great attention, promising to put that blessed Advice in practice; and so continued in a very serious and laudable frame till the time of Execution, which was the 17May, being then conducted to Tyburn with vest numbers of people following the Carts to behold the last sad Scene of their deplorable Tragedy. Being come to the Gallows, and the usual Prayers and Solemnities being performed, one of them spoke a pretty while to the Multitude, protesting, This was the first Face that he was ever actually guilty of, though he had been accessary to divers others, and had been all his days a very ill Liver; so that he could not but acknowledge that he suffer'd justly. He very much admonish'd all persons to consider their ways; especially warning Youth not to misspend their time in Idleness, or Disobedience to Parents or Masters; and to have a care of being seduced and drawn away by led women. affirming that such Courses and their Temptations, and to satisfie their Luxury, had been originally the cause of his destruction, and that shameful death he was now going to suffer. The rest said very few words, unless to some particular Acquaintance; but by their Gestures seemed to pray secretly, and so were all Executed according to Sentence.", 'places': ['TYBURN', 'TYBURN', 'Newgate', 'Virginia', 'England', 'Newgate', 'Newgate', 'Newgate', 'saffron-hill', 'New prison', 'Dukes Place', 'Tyburn'], 'type': 'OA', 'persons': ['Henry Seabrook', 'Elizabeth Longman', 'Robert Scot', 'Edward Wall', 'Edward Russell', 'Henry Seabrook', 'Elizabeth Longman', 'Robert Scot', 'Edward Wall', 'Edward Russell', 'Elizabeth Longman', 'Edward Wall', 'Edward Russel', 'Besse Longman', 'Henry Sea brooke'], 'date': '16760517'} ``` ### Data Fields - `id`: A unique identifier for the data point (in this case, a trial) - `text`: The text of the proceeding - `places`: The places mentioned in the text - `type`: This can be either 'OA' or 'OBP'. OA is "Ordinary's Accounts" and OBP is "Sessions Proceedings" - `persons`: The persons named in the text - `date`: The date of the text ### Data Splits This dataset only contains a single split: Train: `2638` examples ## Dataset Creation ### Curation Rationale Between 1674 and 1913 the Proceedings of the Central Criminal Court in London, the Old Bailey, were published eight times a year. These records detail 197,000 individual trials and contain 127 million words in 182,000 pages. They represent the largest single source of information about non-elite lives and behaviour ever published and provide a wealth of detail about everyday life, as well as valuable systematic evidence of the circumstances surrounding the crimes and lives of victims and the accused, and their trial outcomes. This project created a fully digitised and structured version of all surviving published trial accounts between 1674 and 1913, and made them available as a searchable online resource. ### Source Data #### Initial Data Collection and Normalization Starting with microfilms of the original Proceedings and Ordinary's Accounts, page images were scanned to create high definition, 400dpi TIFF files, from which GIF and JPEG files have been created for transmission over the internet. The uncompressed TIFF files will be preserved for archival purposes and should eventually be accessible over the web once data transmission speeds improve. A GIF format has been used to transmit image files for the Proceedings published between 1674 and 1834. #### Who are the source language producers? The text of the 1674 to October 1834 Proceedings was manually typed by the process known as "double rekeying", whereby the text is typed in twice, by two different typists. Then the two transcriptions are compared by computer. Differences are identified and then resolved manually. This process was also used to create a transcription of the Ordinary's Accounts. This process means this text data contains fewer errors than many historical text corpora produced using Optical Character Recognition. ### Annotations #### Annotation process The markup was done by a combination of automated and manual processes. Most of the 1674 to October 1834 markup was done manually by a team of five data developers working at the Humanities Research Institute at the University of Sheffield (see project staff). However, person names were tagged using an automated markup programme, GATE, developed by the Department of Computer Science at the University of Sheffield and specially customised to process the text of the Proceedings. Most of the 1674-1834 trial proceedings were run through GATE, which was able to identify approximately 80-90% of the names in the text. GATE was asked only to identify names where both a forename (not just an initial) and surname were given. The names not identified by this programme were not regularly marked up manually unless they were the names of defendants or victims. The November 1834 to 1913 text was first run through an automated markup process. This process was carried out by the Digital Humanities Institute Sheffield. Remaining markup, including checking of the results of the automated markup, was carried out by a team of eight data developers employed by the University of Hertfordshire (see project staff). #### Who are the annotators? - The directors of this project, and authors of all the historical background pages, are Professor Clive Emsley (Open University), Professor Tim Hitchcock (University of Sussex) and Professor Robert Shoemaker (University of Sheffield). - The Project Manager is Dr Sharon Howard. - The technical officer responsible for programming the search engines is Jamie McLaughlin. - The Senior Data Developer, in charge of all the tagging procedures, was Dr Philippa Hardman. - The other Data Developers were Anna Bayman, Eilidh Garrett, Carol Lewis-Roylance, Susan Parkinson, Anna Simmons, Gwen Smithson, Nicola Wilcox, and Catherine Wright. - The London researcher was Mary Clayton. - The technical officers responsible for the automated markup were Ed MacKenzie and Katherine Rogers. - Project staff who worked on the 1674-1834 phase of the project include Dr Louise Henson (Senior Data Developer), Dr John Black, Dr Edwina Newman, Kay O'Flaherty, and Gwen Smithson. ### Personal and Sensitive Information -This dataset contains personal information of people involved in criminal proceedings during the time period ## Considerations for Using the Data ### Social Impact of Dataset [Needs More Information] ### Discussion of Biases - "Virtually every aspect of English life between 1674 and 1913 was influenced by gender, and this includes behaviour documented in the Old Bailey Proceedings. Long-held views about the particular strengths, weaknesses, and appropriate responsibilities of each sex shaped everyday lives, patterns of crime, and responses to crime." This dataset contains text that adheres to those stereotypes. - "The make-up of London's population changed and changed again during the course of the two and a half centuries after 1674. European Protestant refugees, blacks discharged from the armies of a growing empire, and Jews from Spain and Eastern Europe, Irish men and women, Lascars and political refugees from the revolutions of the nineteenth century contributed to the ragout of communities that made up this world city. Information about all these communities, and several more besides, can be found in the Proceedings" ### Other Known Limitations ## Additional Information ### Dataset Curators - The directors of this project, and authors of all the historical background pages, are Professor Clive Emsley (Open University), Professor Tim Hitchcock (University of Sussex) and Professor Robert Shoemaker (University of Sheffield). - The Project Manager is Dr Sharon Howard. - The technical officer responsible for programming the search engines is Jamie McLaughlin. - The Senior Data Developer, in charge of all the tagging procedures, was Dr Philippa Hardman. - The other Data Developers were Anna Bayman, Eilidh Garrett, Carol Lewis-Roylance, Susan Parkinson, Anna Simmons, Gwen Smithson, - Nicola Wilcox, and Catherine Wright. ### Licensing Information [CC-NY-04](https://creativecommons.org/licenses/by/4.0/) ### Citation Information @article{Howard2017, author = "Sharon Howard", title = "{Old Bailey Online XML Data}", year = "2017", month = "4", url = "https://figshare.shef.ac.uk/articles/dataset/Old_Bailey_Online_XML_Data/4775434", doi = "10.15131/shef.data.4775434.v2" } Thanks to [@shamikbose](https://github.com/shamikbose) for adding this dataset.
ceyda
null
null
null
false
197
false
ceyda/fashion-products-small
2022-07-21T08:24:03.000Z
null
false
ef520080129df6ec7fda0df347b5f7eacdf0dc1c
[]
[]
https://huggingface.co/datasets/ceyda/fashion-products-small/resolve/main/README.md
For test purposes! Preprocessed version of https://www.kaggle.com/datasets/paramaggarwal/fashion-product-images-dataset Images resized to have max 512
Ericwang
null
null
null
false
12
false
Ericwang/ASAP
2022-07-16T22:07:09.000Z
null
false
2a0ba93f41e56c1d8c1327c47f78b37bfd96f457
[]
[ "license:cc-by-sa-3.0" ]
https://huggingface.co/datasets/Ericwang/ASAP/resolve/main/README.md
--- license: cc-by-sa-3.0 --- The preprocessed asap dataset
diwank
null
@misc{sage2017logodataset, author={Sage, Alexander and Agustsson, Eirikur and Timofte, Radu and Van Gool, Luc}, title = {LLD - Large Logo Dataset - version 0.1}, year = {2017},
Designing a logo for a new brand is a lengthy and tedious back-and-forth process between a designer and a client. In this paper we explore to what extent machine learning can solve the creative task of the designer. For this, we build a dataset -- LLD -- of 600k+ logos crawled from the world wide web. Training Generative Adversarial Networks (GANs) for logo synthesis on such multi-modal data is not straightforward and results in mode collapse for some state-of-the-art methods. We propose the use of synthetic labels obtained through clustering to disentangle and stabilize GAN training. We are able to generate a high diversity of plausible logos and we demonstrate latent space exploration techniques to ease the logo design task in an interactive manner. Moreover, we validate the proposed clustered GAN training on CIFAR 10, achieving state-of-the-art Inception scores when using synthetic labels obtained via clustering the features of an ImageNet classifier. GANs can cope with multi-modal data by means of synthetic labels achieved through clustering, and our results show the creative potential of such techniques for logo synthesis and manipulation.
false
1
false
diwank/lld
2022-08-09T10:48:34.000Z
null
false
6e98d95ddee00d17778472d8e3ad7da227168901
[]
[ "language:en", "license:mit", "multilinguality:monolingual", "size_categories:100K<n<1M" ]
https://huggingface.co/datasets/diwank/lld/resolve/main/README.md
--- language: - en license: - mit multilinguality: - monolingual size_categories: - 100K<n<1M pretty_name: Large Logo Dataset --- # Dataset Card for Large Logo Dataset (LLD) ## Description Adapted from the original [LLD dataset](https://data.vision.ee.ethz.ch/sagea/lld/). Original description: > Designing a logo for a new brand is a lengthy and tedious back-and-forth process between a designer and a client. In this paper we explore to what extent machine learning can solve the creative task of the designer. For this, we build a dataset -- LLD -- of 600k+ logos crawled from the world wide web. Training Generative Adversarial Networks (GANs) for logo synthesis on such multi-modal data is not straightforward and results in mode collapse for some state-of-the-art methods. We propose the use of synthetic labels obtained through clustering to disentangle and stabilize GAN training. We are able to generate a high diversity of plausible logos and we demonstrate latent space exploration techniques to ease the logo design task in an interactive manner. Moreover, we validate the proposed clustered GAN training on CIFAR 10, achieving state-of-the-art Inception scores when using synthetic labels obtained via clustering the features of an ImageNet classifier. GANs can cope with multi-modal data by means of synthetic labels achieved through clustering, and our results show the creative potential of such techniques for logo synthesis and manipulation. ## Schema ``` yaml - name: <string> Name of the company / organization - description: <string> Description of what the organization does - images: <np.uint8, shape(3, 400, 400)> Three logo images of 400x400 ``` ## Citations ``` text @misc{sage2017logodataset, author={Sage, Alexander and Agustsson, Eirikur and Timofte, Radu and Van Gool, Luc}, title = {LLD - Large Logo Dataset - version 0.1}, year = {2017}, howpublished = "\url{https://data.vision.ee.ethz.ch/cvl/lld}"} ```
Muennighoff
null
@article{nllb2022, author = {NLLB Team, Marta R. Costa-jussà, James Cross, Onur Çelebi, Maha Elbayad, Kenneth Heafield, Kevin Heffernan, Elahe Kalbassi, Janice Lam, Daniel Licht, Jean Maillard, Anna Sun, Skyler Wang, Guillaume Wenzek, Al Youngblood, Bapi Akula, Loic Barrault, Gabriel Mejia Gonzalez, Prangthip Hansanti, John Hoffman, Semarley Jarrett, Kaushik Ram Sadagopan, Dirk Rowe, Shannon Spruit, Chau Tran, Pierre Andrews, Necip Fazil Ayan, Shruti Bhosale, Sergey Edunov, Angela Fan, Cynthia Gao, Vedanuj Goswami, Francisco Guzmán, Philipp Koehn, Alexandre Mourachko, Christophe Ropers, Safiyyah Saleem, Holger Schwenk, Jeff Wang}, title = {No Language Left Behind: Scaling Human-Centered Machine Translation}, year = {2022} }
>The creation of FLORES200 doubles the existing language coverage of FLORES-101. Given the nature of the new languages, which have less standardization and require more specialized professional translations, the verification process became more complex. This required modifications to the translation workflow. FLORES-200 has several languages which were not translated from English. Specifically, several languages were translated from Spanish, French, Russian and Modern Standard Arabic. Moreover, FLORES-200 also includes two script alternatives for four languages. FLORES-200 consists of translations from 842 distinct web articles, totaling 3001 sentences. These sentences are divided into three splits: dev, devtest, and test (hidden). On average, sentences are approximately 21 words long.
false
2,541
false
Muennighoff/flores200
2022-10-25T08:11:38.000Z
flores
false
c43c9e247f96a99e813ab6f406b531544be4d77b
[]
[ "arxiv:2207.04672", "annotations_creators:found", "language_creators:expert-generated", "license:cc-by-sa-4.0", "multilinguality:multilingual", "multilinguality:translation", "size_categories:unknown", "source_datasets:extended|flores", "task_categories:text2text-generation", "task_categories:tran...
https://huggingface.co/datasets/Muennighoff/flores200/resolve/main/README.md
--- annotations_creators: - found language_creators: - expert-generated license: - cc-by-sa-4.0 multilinguality: - multilingual - translation size_categories: - unknown source_datasets: - extended|flores task_categories: - text2text-generation - translation task_ids: [] paperswithcode_id: flores pretty_name: flores200 tags: - conditional-text-generation --- # Dataset Card for Flores200 ## Table of Contents - [Dataset Card for Flores200](#dataset-card-for-flores200) - [Table of Contents](#table-of-contents) - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) ## Dataset Description - **Home:** [Flores](https://github.com/facebookresearch/flores) - **Repository:** [Github](https://github.com/facebookresearch/flores) ### Dataset Summary FLORES is a benchmark dataset for machine translation between English and low-resource languages. >The creation of FLORES200 doubles the existing language coverage of FLORES-101. Given the nature of the new languages, which have less standardization and require more specialized professional translations, the verification process became more complex. This required modifications to the translation workflow. FLORES-200 has several languages which were not translated from English. Specifically, several languages were translated from Spanish, French, Russian and Modern Standard Arabic. Moreover, FLORES-200 also includes two script alternatives for four languages. FLORES-200 consists of translations from 842 distinct web articles, totaling 3001 sentences. These sentences are divided into three splits: dev, devtest, and test (hidden). On average, sentences are approximately 21 words long. **Disclaimer**: *The Flores200 dataset is hosted by the Facebook and licensed under the [Creative Commons Attribution-ShareAlike 4.0 International License](https://creativecommons.org/licenses/by-sa/4.0/). ### Supported Tasks and Leaderboards #### Multilingual Machine Translation Refer to the [Dynabench leaderboard](https://dynabench.org/flores/Flores%20MT%20Evaluation%20(FULL)) for additional details on model evaluation on FLORES-101 in the context of the WMT2021 shared task on [Large-Scale Multilingual Machine Translation](http://www.statmt.org/wmt21/large-scale-multilingual-translation-task.html). Flores 200 is an extention of this. ### Languages The dataset contains parallel sentences for 200 languages, as mentioned in the original [Github](https://github.com/facebookresearch/flores/blob/master/README.md) page for the project. Languages are identified with the ISO 639-3 code (e.g. `eng`, `fra`, `rus`) plus an additional code describing the script (e.g., "eng_Latn", "ukr_Cyrl"). See [the webpage for code descriptions](https://github.com/facebookresearch/flores/blob/main/flores200/README.md). Use the configuration `all` to access the full set of parallel sentences for all the available languages in a single command. Use a hyphenated pairing to get two langauges in one datapoint (e.g., "eng_Latn-ukr_Cyrl" will provide sentences in the format below). ## Dataset Structure ### Data Instances A sample from the `dev` split for the Russian language (`ukr_Cyrl` config) is provided below. All configurations have the same structure, and all sentences are aligned across configurations and splits. ```python { 'id': 1, 'sentence': 'У понеділок, науковці зі Школи медицини Стенфордського університету оголосили про винайдення нового діагностичного інструменту, що може сортувати клітини за їх видами: це малесенький друкований чіп, який можна виготовити за допомогою стандартних променевих принтерів десь по одному центу США за штуку.', 'URL': 'https://en.wikinews.org/wiki/Scientists_say_new_medical_diagnostic_chip_can_sort_cells_anywhere_with_an_inkjet', 'domain': 'wikinews', 'topic': 'health', 'has_image': 0, 'has_hyperlink': 0 } ``` When using a hyphenated pairing or using the `all` function, data will be presented as follows: ```python { 'id': 1, 'URL': 'https://en.wikinews.org/wiki/Scientists_say_new_medical_diagnostic_chip_can_sort_cells_anywhere_with_an_inkjet', 'domain': 'wikinews', 'topic': 'health', 'has_image': 0, 'has_hyperlink': 0, 'sentence_eng_Latn': 'On Monday, scientists from the Stanford University School of Medicine announced the invention of a new diagnostic tool that can sort cells by type: a tiny printable chip that can be manufactured using standard inkjet printers for possibly about one U.S. cent each.', 'sentence_ukr_Cyrl': 'У понеділок, науковці зі Школи медицини Стенфордського університету оголосили про винайдення нового діагностичного інструменту, що може сортувати клітини за їх видами: це малесенький друкований чіп, який можна виготовити за допомогою стандартних променевих принтерів десь по одному центу США за штуку.' } ``` The text is provided as-in the original dataset, without further preprocessing or tokenization. ### Data Fields - `id`: Row number for the data entry, starting at 1. - `sentence`: The full sentence in the specific language (may have _lang for pairings) - `URL`: The URL for the English article from which the sentence was extracted. - `domain`: The domain of the sentence. - `topic`: The topic of the sentence. - `has_image`: Whether the original article contains an image. - `has_hyperlink`: Whether the sentence contains a hyperlink. ### Data Splits | config| `dev`| `devtest`| |-----------------:|-----:|---------:| |all configurations| 997| 1012:| ### Dataset Creation Please refer to the original article [No Language Left Behind: Scaling Human-Centered Machine Translation](https://arxiv.org/abs/2207.04672) for additional information on dataset creation. ## Additional Information ### Dataset Curators See paper for details. ### Licensing Information Licensed with Creative Commons Attribution Share Alike 4.0. License available [here](https://creativecommons.org/licenses/by-sa/4.0/). ### Citation Information Please cite the authors if you use these corpora in your work: ```bibtex @article{nllb2022, author = {NLLB Team, Marta R. Costa-jussà, James Cross, Onur Çelebi, Maha Elbayad, Kenneth Heafield, Kevin Heffernan, Elahe Kalbassi, Janice Lam, Daniel Licht, Jean Maillard, Anna Sun, Skyler Wang, Guillaume Wenzek, Al Youngblood, Bapi Akula, Loic Barrault, Gabriel Mejia Gonzalez, Prangthip Hansanti, John Hoffman, Semarley Jarrett, Kaushik Ram Sadagopan, Dirk Rowe, Shannon Spruit, Chau Tran, Pierre Andrews, Necip Fazil Ayan, Shruti Bhosale, Sergey Edunov, Angela Fan, Cynthia Gao, Vedanuj Goswami, Francisco Guzmán, Philipp Koehn, Alexandre Mourachko, Christophe Ropers, Safiyyah Saleem, Holger Schwenk, Jeff Wang}, title = {No Language Left Behind: Scaling Human-Centered Machine Translation}, year = {2022} } ```
Maxmioti
null
null
null
false
1
false
Maxmioti/GDRP-fines
2022-07-17T10:03:34.000Z
null
false
85b9612b440ac0158d5722d0d45b849a012468ec
[]
[ "license:other" ]
https://huggingface.co/datasets/Maxmioti/GDRP-fines/resolve/main/README.md
--- license: other --- Opensource DataSet form a Kaggle competition https://www.kaggle.com/datasets/andreibuliga1/gdpr-fines-20182020-updated-23012021 GDPR-fines is a dataset with summary of GDPR cases from companies that were find between 2018 and 2021. You will find the summary plus the Articles violated in the cases (3 most importants + "Others" regrouping the rest of articles). Raw text and lemmatized text available plus multi-labels.
erikanesse
null
null
null
false
1
false
erikanesse/great_books
2022-07-17T13:47:12.000Z
null
false
20aac0fbc008c17c735fe27c2eb410edbdc84381
[]
[ "license:unlicense" ]
https://huggingface.co/datasets/erikanesse/great_books/resolve/main/README.md
--- license: unlicense --- # Dataset Summary The Great Books dataset is a set of texts based on the [St. John's College Great Books Program](https://www.sjc.edu/academic-programs/undergraduate/classes/seminar/annapolis-undergraduate-readings). It includes 83 works from authors on the Program.
noob123
null
null
null
false
2
false
noob123/imdb10000
2022-07-17T13:33:20.000Z
null
false
630cc1387afa15f1d91d99f27e061b2a7cf39a0a
[]
[]
https://huggingface.co/datasets/noob123/imdb10000/resolve/main/README.md
Muennighoff
null
@article{muennighoff2022crosslingual, title={Crosslingual Generalization through Multitask Finetuning}, author={Muennighoff, Niklas and Wang, Thomas and Sutawika, Lintang and Roberts, Adam and Biderman, Stella and Scao, Teven Le and Bari, M Saiful and Shen, Sheng and Yong, Zheng-Xin and Schoelkopf, Hailey and others}, journal={arXiv preprint arXiv:2211.01786}, year={2022} } @misc{tikhonov2021heads, title={It's All in the Heads: Using Attention Heads as a Baseline for Cross-Lingual Transfer in Commonsense Reasoning}, author={Alexey Tikhonov and Max Ryabinin}, year={2021}, eprint={2106.12066}, archivePrefix={arXiv}, primaryClass={cs.CL} }
A multilingual collection of Winograd Schemas in six languages that can be used for evaluation of cross-lingual commonsense reasoning capabilities.
false
85
false
Muennighoff/xwinograd
2022-11-15T20:14:48.000Z
null
false
0215d1ea0a32e69f595e44f67ba6770be7cab400
[]
[ "arxiv:2106.12066", "language:en", "language:fr", "language:ja", "language:pt", "language:ru", "language:zh" ]
https://huggingface.co/datasets/Muennighoff/xwinograd/resolve/main/README.md
--- language: - en - fr - ja - pt - ru - zh --- ## XWinograd Multilingual winograd schema challenge. ### Languages & Samples - "en": 2325 - "fr": 83 - "jp": 959 - "pt": 263 - "ru": 315 - "zh": 504 ### Dataset creation Winograd schema challenges come from the XWinograd dataset introduced in Tikhonov et al. As it only contains 16 Chinese schemas, we add 488 Chinese schemas from `clue/cluewsc2020`. If you only want the original xWinograd Chinese schemas, do: `load_dataset("Muennighoff/xwinograd", "zh")["test"][0][:16]` ## Additional Information ### Citation Information ```bibtex @article{muennighoff2022crosslingual, title={Crosslingual Generalization through Multitask Finetuning}, author={Muennighoff, Niklas and Wang, Thomas and Sutawika, Lintang and Roberts, Adam and Biderman, Stella and Scao, Teven Le and Bari, M Saiful and Shen, Sheng and Yong, Zheng-Xin and Schoelkopf, Hailey and others}, journal={arXiv preprint arXiv:2211.01786}, year={2022} } ``` ```bibtex @misc{tikhonov2021heads, title={It's All in the Heads: Using Attention Heads as a Baseline for Cross-Lingual Transfer in Commonsense Reasoning}, author={Alexey Tikhonov and Max Ryabinin}, year={2021}, eprint={2106.12066}, archivePrefix={arXiv}, primaryClass={cs.CL} } ``` ### Contributions Thanks to Jordan Clive, @yongzx & @khalidalt for support on adding Chinese.
pyronear
null
@software{Pyronear_PyroVision_2019, title={Pyrovision: wildfire early detection}, author={Pyronear contributors}, year={2019}, month={October}, publisher = {GitHub}, url = {https://github.com/pyronear/pyro-vision} }
OpenFire is an image classification dataset for wildfire detection, collected from web searches.
false
5
false
pyronear/openfire
2022-07-17T23:42:06.000Z
null
false
e75c387721d7b6402b8c0b4ef5dab3ab0cd3ec61
[]
[ "annotations_creators:crowdsourced", "language_creators:crowdsourced", "license:apache-2.0", "size_categories:1K<n<10K", "source_datasets:original", "task_categories:image-classification", "task_ids:image-classification" ]
https://huggingface.co/datasets/pyronear/openfire/resolve/main/README.md
--- annotations_creators: - crowdsourced language: [] language_creators: - crowdsourced license: - apache-2.0 multilinguality: [] pretty_name: Wildfire image classification dataset collected using images from web searches. size_categories: - 1K<n<10K source_datasets: - original task_categories: - image-classification task_ids: - image-classification --- # Dataset Card for OpenFire ## Table of Contents - [Table of Contents](#table-of-contents) - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - **Homepage:** https://pyronear.org/pyro-vision/datasets.html#openfire - **Repository:** https://github.com/pyronear/pyro-vision - **Point of Contact:** Pyronear <https://pyronear.org/en/> ### Dataset Summary OpenFire is an image classification dataset for wildfire detection, collected from web searches. ### Supported Tasks and Leaderboards - `image-classification`: The dataset can be used to train a model for Image Classification. ### Languages English ## Dataset Structure ### Data Instances A data point comprises an image URL and its binary label. ``` { 'image_url': 'https://cdn-s-www.ledauphine.com/images/13C08274-6BA6-4577-B3A0-1E6C1B2A573C/FB1200/photo-1338240831.jpg', 'is_wildfire': true, } ``` ### Data Fields - `image_url`: the download URL of the image. - `is_wildfire`: a boolean value specifying whether there is an ongoing wildfire on the image. ### Data Splits The data is split into training and validation sets. The training set contains 7143 images and the validation set 792 images. ## Dataset Creation ### Curation Rationale The curators state that the current wildfire classification datasets typically contain close-up shots of wildfires, with limited variations of weather conditions, luminosity and backrgounds, making it difficult to assess for real world performance. They argue that the limitations of datasets have partially contributed to the failure of some algorithms in coping with sun flares, foggy / cloudy weather conditions and small scale. ### Source Data #### Initial Data Collection and Normalization OpenFire was collected using images publicly indexed by the search engine DuckDuckGo using multiple relevant queries. The images were then manually cleaned to remove errors. ### Annotations #### Annotation process Each web search query was designed to yield a single label (with wildfire or without), and additional human verification was used to remove errors. #### Who are the annotators? François-Guillaume Fernandez ### Personal and Sensitive Information [More Information Needed] ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed] ### Discussion of Biases [More Information Needed] ### Other Known Limitations [More Information Needed] ## Additional Information ### Dataset Curators François-Guillaume Fernandez ### Licensing Information [Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0). ### Citation Information ``` @software{Pyronear_PyroVision_2019, title={Pyrovision: wildfire early detection}, author={Pyronear contributors}, year={2019}, month={October}, publisher = {GitHub}, howpublished = {\url{https://github.com/pyronear/pyro-vision}} } ```
shamikbose89
null
@article{de2015corpus, title={Corpus of Late Modern English texts (version 3.1)}, author={De Smet, Hendrik and Flach, Susanne and Tyrkk{\"o}, Jukka and Diller, Hans-J{\"u}rgen}, year={2015} }
The Corpus of Late Modern English Texts, version 3.1 (CLMET3.1) has been created by Hendrik De Smet, Susanne Flach, Hans-Jürgen Diller and Jukka Tyrkkö, as an offshoot of a bigger project developing a database of text descriptors (Diller, De Smet & Tyrkkö 2011). CLMET3.1 is a principled collection of public domain texts drawn from various online archiving projects. This dataset can be used for part-of-speech tagging, NER and text classification
false
1
false
shamikbose89/clmet_3_1
2022-07-18T02:14:38.000Z
null
false
3f8fe90b59fe1958fe39583b5d74e398d882f1ed
[]
[ "annotations_creators:expert-generated", "annotations_creators:machine-generated", "language:en", "language_creators:found", "license:cc-by-sa-4.0", "multilinguality:monolingual", "size_categories:n<1K", "source_datasets:original", "task_categories:text-classification", "task_categories:fill-mask"...
https://huggingface.co/datasets/shamikbose89/clmet_3_1/resolve/main/README.md
--- annotations_creators: - expert-generated - machine-generated language: - 'en' language_creators: - found paperswithcode_id: null license: - cc-by-sa-4.0 multilinguality: - monolingual pretty_name: 'Corpus of Late Modern English Texts v3.1' size_categories: - n<1K source_datasets: - original task_categories: - text-classification - fill-mask task_ids: - multi-label-classification - masked-language-modeling --- # Dataset Card for clmet_3_1 **NOTES**: - Some of the annotations in the `class` and `pos` configs are not properly formed. These are indicated with warning messages when the dataset is loaded. - In addition to the classes mentioned in the README for the dataset, there is an additional class in the `class` dataset called `QUOT`. As far as I can tell, this is used for tagging all quotation marks - When the `class` and `pos` configs are loaded, the available class/pos tags are shown at the top ## Dataset Statistics: The following table summarises the corpus make-up: |PERIOD | #authors | #texts |CQP3.1 | non-PUNC | |-----------|----------|---------------------|--------|---------| |1710-1780 | 51 | 88 | 12,182,064 | 10,415,721| |1780-1850 | 70 | 99 | 13,300,457 | 11,269,977| |1850-1920 | 91 | 146 | 14,858,239 | 12,657,159| |TOTAL | 212 | 333 | 40,340,760 | 34,342,857| |GENRE (all tokens):| | | | |---|---|---|---| | | **1710-1780**| **1780-1850** | **1850-1920** | |Narrative fiction | 5,405,645 | 5,780,352 | 7,561,339 | |Narrative non-fiction | 2,145,946 | 2,261,485 | 1,097,487 | |Drama | 523,318 | 441,040 | 763,352 | |Letters | 1,208,219 | 842,795 | 554,046 | |Treatise | 1,263,090 | 1,927,272 | 2,030,210 | |Other | 1,635,846 | 2,047,513 | 2,851,805 | ## Table of Contents - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-instances) - [Data Splits](#data-instances) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) ## Dataset Description - **Homepage:** http://fedora.clarin-d.uni-saarland.de/clmet/clmet.html - **Repository:** [Needs More Information] - **Paper:** https://icame.info/icame_static/ij29/ij29-page69-82.pdf - **Leaderboard:** [Needs More Information] - **Point of Contact:** [Henrik De Smet](https://www.arts.kuleuven.be/ling/func/members/hendrik-desmet/func) ### Dataset Summary The Corpus of Late Modern English Texts, version 3.1 (CLMET3.1) has been created by Hendrik De Smet, Susanne Flach, Hans-J�rgen Diller and Jukka Tyrkk�, as an offshoot of a bigger project developing a database of text descriptors (Diller, De Smet & Tyrkk� 2011). CLMET3.1 is a principled collection of public domain texts drawn from various online archiving projects. In total, the corpus contains some 34 million words of running text. It incorporates CLMET, CLMETEV, and CLMET3.0, and has been compiled following roughly the same principles, that is: - The corpus covers the period 17101920, divided into three 70-year sub-periods. - The texts making up the corpus have all been written by British and Irish authors who are native speakers of English. - The corpus never contains more than three texts by the same author. - The texts within each sub-period have been written by authors born within a correspondingly restricted sub-period. ### Supported Tasks and Leaderboards - `named-entity-recognition`: Since this dataset is tagged, it can be used for performing NER - `text-classification`: Each text comes with the date of the text and can be used to perform stylistic classification of texts ### Languages The text in the dataset is in English. The associated BCP-47 code is `en` ## Dataset Structure ### Data Instances A `plain` sample looks as follows: ``` {'text': "\nFAME AND THE POET\n \nDRAMATIS PERSONAE�\n \nHarry de Reves , a Poet .\n \n( This name , though of course of French origin , has become anglicised and is pronounced de Reevs . )\n \nDick Prattle , a Lieutenant-Major of the Royal Horse Marines .\n \nFame .\n \nScene\n \nThe Poet 's rooms in London .\nWindows in back .\nA high screen in a corner .\n \nTime : February 30th .\n \nThe Poet is sitting at a table writing .\n \n[ Enter Dick Prattle .\n \nPrattle : Hullo , Harry .\n \nde Reves : Hullo , Dick .\nGood Lord , where are you from ?\n \nPrattle ( casually ) : The ends of the earth .\n \nde Reves : Well , I 'm damned !\n \nPrattle : Thought I 'd drop in and see how you were getting on .\n \nde Reves : Well , that 's splendid .\nWhat are you doing in London ?\n \nPrattle : Well , I wanted to see if I could get one or two decent ties to wear - you can get nothing out there - then I thought I 'd have a look and see how London was getting on .\n \nde Reves : Splendid !\nHow 's everybody ?\n \nPrattle : All going strong .\n \nde Reves : That 's good .\n \nPrattle ( seeing paper and ink ) : But what are you doing ?\n \nde Reves : Writing .\n \nPrattle : Writing ?\nI did n't know you wrote .\n \nde Reves : Yes , I 've taken to it rather .\n \nPrattle : I say - writing 's no good .\nWhat do you write ?\n \nde Reves : Oh , poetry .\n \nPrattle : Poetry !\nGood Lord !\n \nde Reves : Yes , that sort of thing , you know .\n \nPrattle : Good Lord !\nDo you make any money by it ?\n \nde Reves : No .\nHardly any .\n \nPrattle : I say - why do n't you chuck it ?\n \nde Reves : Oh , I do n't know .\nSome people seem to like my stuff , rather .\nThat 's why I go on .\n \nPrattle : I 'd chuck it if there 's no money in it .\n \nde Reves : Ah , but then it 's hardly in your line , is it ?\nYou 'd hardly approve of poetry if there was money in it .\n \nPrattle : Oh , I do n't say that .\nIf I could make as much by poetry as I can by betting I do n't say I would n't try the poetry touch , only - -\n \nde Reves : Only what ?\n \nPrattle : Oh , I do n't know .\nOnly there seems more sense in betting , somehow .\n \nde Reves : Well , yes .\nI suppose it 's easier to tell what an earthly horse is going to do , than to tell what Pegasus - -\n \nPrattle : What 's Pegasus ?\n \nde Reves : Oh , the winged horse of poets .\n \nPrattle : I say !\nYou do n't believe in a winged horse , do you ?\n \nde Reves : In our trade we believe in all fabulous things .\nThey all represent some large truth to us .\nAn emblem like Pegasus is as real a thing to a poet as a Derby winner would be to you .\n \nPrattle : I say .\n( Give me a cigarette .\nThanks . )\nWhat ?\nThen you 'd believe in nymphs and fauns , and Pan , and all those kind of birds ?\n \nde Reves : Yes .\nYes .\nIn all of them .\n \nPrattle : Good Lord !\n \nde Reves : You believe in the Lord Mayor of London , do n't you ?\n \nPrattle : Yes , of course ; but what has - -\n \nde Reves : Four million people or so made him Lord Mayor , did n't they ?\nAnd he represents to them the wealth and dignity and tradition of - -\n \nPrattle : Yes ; but , I say , what has all this - -\n \nde Reves : Well , he stands for an idea to them , and they made him Lord Mayor , and so he is one ...\n \nPrattle : Well , of course he is .\n \nde Reves : In the same way Pan has been made what he is by millions ; by millions to whom he represents world-old traditions .\n \nPrattle ( rising from his chair and stepping backwards , laughing and looking at the Poet in a kind of assumed wonder ) : I say ... I say ... You old heathen ... but Good Lord ...\n \n[ He bumps into the high screen behind , pushing it back a little .\n \nde Reves : Look out !\nLook out !\n \nPrattle : What ?\nWhat 's the matter ?\n \nde Reves : The screen !\n \nPrattle : Oh , sorry , yes .\nI 'll put it right .\n \n[ He is about to go round behind it .\n \nde Reves : No , do n't go round there .\n \nPrattle : What ?\nWhy not ?\n \nde Reves : Oh , you would n't understand .\n \nPrattle : Would n't understand ?\nWhy , what have you got ?\n \nde Reves : Oh , one of those things ... You would n't understand .\n \nPrattle : Of course I 'd understand .\nLet 's have a look .\n \n[ The Poet walks towards Prattle and the screen .\nHe protests no further .\nPrattle looks round the corner of the screen .\n \nAn altar .\n \nde Reves ( removing the screen altogether ) : That is all .\nWhat do you make of it ?\n \n[ An altar of Greek design , shaped like a pedestal , is revealed .\nPapers litter the floor all about it .\n \nPrattle : I say - you always were an untidy devil .\n \nde Reves : Well , what do you make of it ?\n \nPrattle : It reminds me of your room at Eton .\n \nde Reves : My room at Eton ?\n \nPrattle : Yes , you always had papers all over your floor .\n \nde Reves : Oh , yes - -\n \nPrattle : And what are these ?\n \nde Reves : All these are poems ; and this is my altar to Fame .\n \nPrattle : To Fame ?\n \nde Reves : The same that Homer knew .\n \nPrattle : Good Lord !\n \nde Reves : Keats never saw her .\nShelley died too young .\nShe came late at the best of times , now scarcely ever .\n \nPrattle : But , my dear fellow , you do n't mean that you think there really is such a person ?\n \nde Reves : I offer all my songs to her .\n \nPrattle : But you do n't mean you think you could actually see Fame ?\n \nde Reves : We poets personify abstract things , and not poets only but sculptors7 and painters too .\nAll the great things of the world are those abstract things .\n \nPrattle : But what I mean is , they 're not really there , like you or me .\n \nde Reves : To us these things are more real than men , they outlive generations , they watch the passing of kingdoms : we go by them like dust ; they are still there , unmoved , unsmiling .\n \nPrattle : But , but , you ca n't think that you could see Fame , you do n't expect to see it ?\n \nde Reves : Not to me .\nNever to me .\nShe of the golden trumpet and Greek dress will never appear to me ... We all have our dreams .\n \nPrattle : I say - what have you been doing all day ?\n \nde Reves : I ?\nOh , only writing a sonnet .\n \nPrattle : Is it a long one ?\n \nde Reves : Not very .\n \nPrattle : About how long is it ?\n \nde Reves : About fourteen lines .\n \nPrattle ( impressively ) : I tell you what it is .\n \nde Reves : Yes ?\n \nPrattle : I tell you what .\nYou 've been overworking yourself .\nI once got like that on board the Sandhurst , working for the passing-out exam .\nI got so bad that I could have seen anything .\n \nde Reves : Seen anything ?\n \nPrattle : Lord , yes ; horned pigs , snakes with wings ; anything ; one of your winged horses even .\nThey gave me some stuff called bromide for it .\nYou take a rest .\n \nde Reves : But my dear fellow , you do n't understand at all .\nI merely said that abstract things are to a poet as near and real and visible as one of your bookmakers or barmaids .\n \nPrattle : I know .\nYou take a rest .\n \nde Reves : Well , perhaps I will .\nI 'd come with you to that musical comedy you 're going to see , only I 'm a bit tired after writing this ; it 's a tedious job .\nI 'll come another night .\n \nPrattle : How do you know I 'm going to see a musical comedy ?\n \nde Reves : Well , where would you go ?\nHamlet 's 8 on at the Lord Chamberlain 's .\nYou 're not going there .\n \nPrattle : Do I look like it ?\n \nde Reves : No .\n \nPrattle : Well , you 're quite right .\nI 'm going to see `` The Girl from Bedlam . ''\nSo long .\nI must push off now .\nIt 's getting late .\nYou take a rest .\nDo n't add another line to that sonnet ; fourteen 's quite enough .\nYou take a rest .\nDo n't have any dinner to-night , just rest .\nI was like that once myself .\nSo long .\n \nde Reves : So long .\n \n[ Exit Prattle .\nde Reves returns to his table and sits down .\n \nGood old Dick !\nHe 's the same as ever .\nLord , how time passes .\n \nHe takes his pen and his sonnet and makes a few alterations .\n \nWell , that 's finished .\nI ca n't do any more to it .\n \n[ He rises and goes to the screen ; he draws back part of it and goes up to the altar .\nHe is about to place his sonnet reverently at the foot of the altar amongst his other verses .\n \nNo , I will not put it there .\nThis one is worthy of the altar .\n \n[ He places the sonnet upon the altar itself .\n \nIf that sonnet does not give me fame , nothing that I have done before will give it to me , nothing that I ever will do .\n \n[ He replaces the screen and returns to his chair at the table .\nTwilight is coming on .\nHe sits with his elbow on the table , his head on his hand , or however the actor pleases .\n \nWell , well .\nFancy seeing Dick again .\nWell , Dick enjoys his life , so he 's no fool .\nWhat was that he said ?\n`` There 's no money in poetry .\nYou 'd better chuck it . ''\nTen years ' work and what have I to show for it ?\nThe admiration of men who care for poetry , and how many of them are there ?\nThere 's a bigger demand for smoked glasses to look at eclipses of the sun .\nWhy should Fame come to me ?\nHave n't I given up my days for her ?\nThat is enough to keep her away .\nI am a poet ; that is enough reason for her to slight me .\nProud and aloof and cold as marble , what does Fame care for us ?\nYes , Dick is right .\nIt 's a poor game chasing illusions , hunting the intangible , pursuing dreams .\nDreams ?\nWhy , we are ourselves dreams .\n \n[ He leans back in his chair .\n \nWe are such stuff As dreams are made on , and our little life Is rounded with a sleep .\n[ He is silent for a while .\nSuddenly he lifts his head .\n \nMy room at Eton , Dick said .\nAn untidy mess .\n \n[ As he lifts his head and says these words , twilight gives place to broad daylight , merely as a hint that the author of the play may have been mistaken , and the whole thing may have been no more than a poet 's dream .\n \nSo it was , and it 's an untidy mess there ( looking at screen ) too .\nDick 's right .\nI 'll tidy it up .\nI 'll burn the whole damned heap ,\n \n[ He advances impetuously towards the screen .\n \nevery damned poem that I was ever fool enough to waste my time on .\n \n[ He pushes back the screen .\nFame in a Greek dress with a long golden trumpet in her hand is seen standing motionless on the altar like a marble goddess .\n \nSo ... you have come !\n \n[ For a while he stands thunderstruck .\nThen he approaches the altar .\n \nDivine fair lady , you have come .\n \n[ He holds up his hand to her and leads her down from the altar and into the centre of the stage .\nAt whatever moment the actor finds it most convenient , he repossesses himself of the sonnet that he had placed on the altar .\nHe now offers it to Fame .\n \nThis is my sonnet .\nIs it well done ?\n \n[ Fame takes it and reads it in silence , while the Poet watches her rapturously .\n \nFame : You 're a bit of all right .\n \nde Reves : What ?\n \nFame : Some poet .\n \nde Reves : I - I - scarcely ... understand .\n \nFame : You 're IT .\n \nde Reves : But ... it is not possible ... are you she that knew Homer ?\n \nFame : Homer ?\nLord , yes .\nBlind old bat , ' e could n't see a yard .\n \nde Reves : O Heavens !\n \n[ Fame walks beautifully to the window .\nShe opens it and puts her head out .\n \nFame ( in a voice with which a woman in an upper storey would cry for help if the house was well alight ) : Hi !\nHi !\nBoys !\nHi !\nSay , folks !\nHi !\n \n[ The murmur of a gathering crowd is heard .\nFame blows her trumpet .\n \nFame : Hi , he 's a poet !\n( Quickly , over her shoulder . )\nWhat 's your name ?\n \nde Reves : De Reves .\n \nFame : His name 's de Reves .\n \nde Reves : Harry de Reves .\n \nFame : His pals call him Harry .\n \nThe Crowd : Hooray !\nHooray !\nHooray !\n \nFame : Say , what 's your favourite colour ?\n \nde Reves : I ... I ... I do n't quite understand .\n \nFame : Well , which do you like best , green or blue ?\n \nde Reves : Oh - er - blue .\n \n[ She blows her trumpet out of the window .\n \nNo - er - I think green .\n \nFame : Green is his favourite colour .\n \nThe Crowd : Hooray !\nHooray !\nHooray !\n \nFame : ` Ere , tell us something .\nThey want to know all about yer .\n \nde Reves : Would n't 9 you perhaps ... would they care to hear my sonnet , if you would - er ...\n \nFame ( picking up quill ) : Here , what 's this ?\n \nde Reves : Oh , that 's my pen .\n \nFame ( after another blast on her trumpet ) : He writes with a quill .\n \n[ Cheers from the Crowd .\n \nFame ( going to a cupboard ) : Here , what have you got in here ?\n \nde Reves : Oh ... er ... those are my breakfast things .\n \nFame ( finding a dirty plate ) : What have yer had on this one ?\n \nde Reves ( mournfully ) : Oh , eggs and bacon .\n \nFame ( at the window ) : He has eggs and bacon for breakfast .\n \nThe Crowd : Hip hip hip , hooray !\nHip hip hip , hooray !\nHip hip hip , hooray !\nFame : Hi , and what 's this ?\n \nde Reves ( miserably ) : Oh , a golf stick .\n \nFame : He 's a man 's man !\nHe 's a virile man !\nHe 's a manly man !\n \n[ Wild cheers from the Crowd , this time only from women 's voices .\n \nde Reves : Oh , this is terrible .\nThis is terrible .\nThis is terrible .\n \n[ Fame gives another peal on her horn .\nShe is about to speak .\n \nde Reves ( solemnly and mournfully ) : One moment , one moment ...\n \nFame : Well , out with it .\n \nde Reves : For ten years , divine lady , I have worshipped you , offering all my songs ... I find ... I find I am not worthy ...\n \nFame : Oh , you 're all right .\n \nde Reves : No , no , I am not worthy .\nIt can not be .\nIt can not possibly be .\nOthers deserve you more .\nI must say it !\nI can not possibly love you .\nOthers are worthy .\nYou will find others .\nBut I , no , no , no .\nIt can not be .\nIt can not be .\nOh , pardon me , but it must not .\n \n[ Meanwhile Fame has been lighting one of his cigarettes .\nShe sits in a comfortable chair , leans right back , and puts her feet right up on the table amongst the poet 's papers .\n \nOh , I fear I offend you .\nBut - it can not be .\n \nFame : Oh , that 's all right , old bird ; no offence .\nI ai n't going to leave you .\n \nde Reves : But - but - but - I do not understand .\n \nFame : I 've come to stay , I have .\n \n[ She blows a puff of smoke through her trumpet .\n \nCURTAIN .\n", 'genre': 'Drama', 'subgenre': 'drama', 'year': '1919', 'quarter_cent': '1900-1924', 'decade': '1910s', 'title': 'Fame and the poet', 'author': 'Dunsany [Edward John Moreton Drax Plunkett]', 'notes': '', 'comments': 'selected from larger file', 'period': '1850-1920', 'id': '317'} ``` A `pos` sample looks as follows: ``` {'text': ['FAME', 'AND', 'THE', 'POET', 'DRAMATIS', 'PERSONAE�', 'Harry', 'de', 'Reves', ',', 'a', 'Poet', '.', '(', 'This', 'name', ',', 'though', 'of', 'course', 'of', 'French', 'origin', ',', 'has', 'become', 'anglicised', 'and', 'is', 'pronounced', 'de', 'Reevs', '.', ')', 'Dick', 'Prattle', ',', 'a', 'Lieutenant-Major', 'of', 'the', 'Royal', 'Horse', 'Marines', '.', 'Fame', '.', 'Scene', 'The', 'Poet', "'s", 'rooms', 'in', 'London', '.', 'Windows', 'in', 'back', '.', 'A', 'high', 'screen', 'in', 'a', 'corner', '.', 'Time', ':', 'February', '30th', '.', 'The', 'Poet', 'is', 'sitting', 'at', 'a', 'table', 'writing', '.', '[', 'Enter', 'Dick', 'Prattle', '.', 'Prattle', ':', 'Hullo', ',', 'Harry', '.', 'de', 'Reves', ':', 'Hullo', ',', 'Dick', '.', 'Good', 'Lord', ',', 'where', 'are', 'you', 'from', '?', 'Prattle', '(', 'casually', ')', ':', 'The', 'ends', 'of', 'the', 'earth', '.', 'de', 'Reves', ':', 'Well', ',', 'I', "'m", 'damned', '!', 'Prattle', ':', 'Thought', 'I', "'d", 'drop', 'in', 'and', 'see', 'how', 'you', 'were', 'getting', 'on', '.', 'de', 'Reves', ':', 'Well', ',', 'that', "'s", 'splendid', '.', 'What', 'are', 'you', 'doing', 'in', 'London', '?', 'Prattle', ':', 'Well', ',', 'I', 'wanted', 'to', 'see', 'if', 'I', 'could', 'get', 'one', 'or', 'two', 'decent', 'ties', 'to', 'wear', '-', 'you', 'can', 'get', 'nothing', 'out', 'there', '-', 'then', 'I', 'thought', 'I', "'d", 'have', 'a', 'look', 'and', 'see', 'how', 'London', 'was', 'getting', 'on', '.', 'de', 'Reves', ':', 'Splendid', '!', 'How', "'s", 'everybody', '?', 'Prattle', ':', 'All', 'going', 'strong', '.', 'de', 'Reves', ':', 'That', "'s", 'good', '.', 'Prattle', '(', 'seeing', 'paper', 'and', 'ink', ')', ':', 'But', 'what', 'are', 'you', 'doing', '?', 'de', 'Reves', ':', 'Writing', '.', 'Prattle', ':', 'Writing', '?', 'I', 'did', "n't", 'know', 'you', 'wrote', '.', 'de', 'Reves', ':', 'Yes', ',', 'I', "'ve", 'taken', 'to', 'it', 'rather', '.', 'Prattle', ':', 'I', 'say', '-', 'writing', "'s", 'no', 'good', '.', 'What', 'do', 'you', 'write', '?', 'de', 'Reves', ':', 'Oh', ',', 'poetry', '.', 'Prattle', ':', 'Poetry', '!', 'Good', 'Lord', '!', 'de', 'Reves', ':', 'Yes', ',', 'that', 'sort', 'of', 'thing', ',', 'you', 'know', '.', 'Prattle', ':', 'Good', 'Lord', '!', 'Do', 'you', 'make', 'any', 'money', 'by', 'it', '?', 'de', 'Reves', ':', 'No', '.', 'Hardly', 'any', '.', 'Prattle', ':', 'I', 'say', '-', 'why', 'do', "n't", 'you', 'chuck', 'it', '?', 'de', 'Reves', ':', 'Oh', ',', 'I', 'do', "n't", 'know', '.', 'Some', 'people', 'seem', 'to', 'like', 'my', 'stuff', ',', 'rather', '.', 'That', "'s", 'why', 'I', 'go', 'on', '.', 'Prattle', ':', 'I', "'d", 'chuck', 'it', 'if', 'there', "'s", 'no', 'money', 'in', 'it', '.', 'de', 'Reves', ':', 'Ah', ',', 'but', 'then', 'it', "'s", 'hardly', 'in', 'your', 'line', ',', 'is', 'it', '?', 'You', "'d", 'hardly', 'approve', 'of', 'poetry', 'if', 'there', 'was', 'money', 'in', 'it', '.', 'Prattle', ':', 'Oh', ',', 'I', 'do', "n't", 'say', 'that', '.', 'If', 'I', 'could', 'make', 'as', 'much', 'by', 'poetry', 'as', 'I', 'can', 'by', 'betting', 'I', 'do', "n't", 'say', 'I', 'would', "n't", 'try', 'the', 'poetry', 'touch', ',', 'only', '-', '-', 'de', 'Reves', ':', 'Only', 'what', '?', 'Prattle', ':', 'Oh', ',', 'I', 'do', "n't", 'know', '.', 'Only', 'there', 'seems', 'more', 'sense', 'in', 'betting', ',', 'somehow', '.', 'de', 'Reves', ':', 'Well', ',', 'yes', '.', 'I', 'suppose', 'it', "'s", 'easier', 'to', 'tell', 'what', 'an', 'earthly', 'horse', 'is', 'going', 'to', 'do', ',', 'than', 'to', 'tell', 'what', 'Pegasus', '-', '-', 'Prattle', ':', 'What', "'s", 'Pegasus', '?', 'de', 'Reves', ':', 'Oh', ',', 'the', 'winged', 'horse', 'of', 'poets', '.', 'Prattle', ':', 'I', 'say', '!', 'You', 'do', "n't", 'believe', 'in', 'a', 'winged', 'horse', ',', 'do', 'you', '?', 'de', 'Reves', ':', 'In', 'our', 'trade', 'we', 'believe', 'in', 'all', 'fabulous', 'things', '.', 'They', 'all', 'represent', 'some', 'large', 'truth', 'to', 'us', '.', 'An', 'emblem', 'like', 'Pegasus', 'is', 'as', 'real', 'a', 'thing', 'to', 'a', 'poet', 'as', 'a', 'Derby', 'winner', 'would', 'be', 'to', 'you', '.', 'Prattle', ':', 'I', 'say', '.', '(', 'Give', 'me', 'a', 'cigarette', '.', 'Thanks', '.', ')', 'What', '?', 'Then', 'you', "'d", 'believe', 'in', 'nymphs', 'and', 'fauns', ',', 'and', 'Pan', ',', 'and', 'all', 'those', 'kind', 'of', 'birds', '?', 'de', 'Reves', ':', 'Yes', '.', 'Yes', '.', 'In', 'all', 'of', 'them', '.', 'Prattle', ':', 'Good', 'Lord', '!', 'de', 'Reves', ':', 'You', 'believe', 'in', 'the', 'Lord', 'Mayor', 'of', 'London', ',', 'do', "n't", 'you', '?', 'Prattle', ':', 'Yes', ',', 'of', 'course', ';', 'but', 'what', 'has', '-', '-', 'de', 'Reves', ':', 'Four', 'million', 'people', 'or', 'so', 'made', 'him', 'Lord', 'Mayor', ',', 'did', "n't", 'they', '?', 'And', 'he', 'represents', 'to', 'them', 'the', 'wealth', 'and', 'dignity', 'and', 'tradition', 'of', '-', '-', 'Prattle', ':', 'Yes', ';', 'but', ',', 'I', 'say', ',', 'what', 'has', 'all', 'this', '-', '-', 'de', 'Reves', ':', 'Well', ',', 'he', 'stands', 'for', 'an', 'idea', 'to', 'them', ',', 'and', 'they', 'made', 'him', 'Lord', 'Mayor', ',', 'and', 'so', 'he', 'is', 'one', '...', 'Prattle', ':', 'Well', ',', 'of', 'course', 'he', 'is', '.', 'de', 'Reves', ':', 'In', 'the', 'same', 'way', 'Pan', 'has', 'been', 'made', 'what', 'he', 'is', 'by', 'millions', ';', 'by', 'millions', 'to', 'whom', 'he', 'represents', 'world-old', 'traditions', '.', 'Prattle', '(', 'rising', 'from', 'his', 'chair', 'and', 'stepping', 'backwards', ',', 'laughing', 'and', 'looking', 'at', 'the', 'Poet', 'in', 'a', 'kind', 'of', 'assumed', 'wonder', ')', ':', 'I', 'say', '...', 'I', 'say', '...', 'You', 'old', 'heathen', '...', 'but', 'Good', 'Lord', '...', '[', 'He', 'bumps', 'into', 'the', 'high', 'screen', 'behind', ',', 'pushing', 'it', 'back', 'a', 'little', '.', 'de', 'Reves', ':', 'Look', 'out', '!', 'Look', 'out', '!', 'Prattle', ':', 'What', '?', 'What', "'s", 'the', 'matter', '?', 'de', 'Reves', ':', 'The', 'screen', '!', 'Prattle', ':', 'Oh', ',', 'sorry', ',', 'yes', '.', 'I', "'ll", 'put', 'it', 'right', '.', '[', 'He', 'is', 'about', 'to', 'go', 'round', 'behind', 'it', '.', 'de', 'Reves', ':', 'No', ',', 'do', "n't", 'go', 'round', 'there', '.', 'Prattle', ':', 'What', '?', 'Why', 'not', '?', 'de', 'Reves', ':', 'Oh', ',', 'you', 'would', "n't", 'understand', '.', 'Prattle', ':', 'Would', "n't", 'understand', '?', 'Why', ',', 'what', 'have', 'you', 'got', '?', 'de', 'Reves', ':', 'Oh', ',', 'one', 'of', 'those', 'things', '...', 'You', 'would', "n't", 'understand', '.', 'Prattle', ':', 'Of', 'course', 'I', "'d", 'understand', '.', 'Let', "'s", 'have', 'a', 'look', '.', '[', 'The', 'Poet', 'walks', 'towards', 'Prattle', 'and', 'the', 'screen', '.', 'He', 'protests', 'no', 'further', '.', 'Prattle', 'looks', 'round', 'the', 'corner', 'of', 'the', 'screen', '.', 'An', 'altar', '.', 'de', 'Reves', '(', 'removing', 'the', 'screen', 'altogether', ')', ':', 'That', 'is', 'all', '.', 'What', 'do', 'you', 'make', 'of', 'it', '?', '[', 'An', 'altar', 'of', 'Greek', 'design', ',', 'shaped', 'like', 'a', 'pedestal', ',', 'is', 'revealed', '.', 'Papers', 'litter', 'the', 'floor', 'all', 'about', 'it', '.', 'Prattle', ':', 'I', 'say', '-', 'you', 'always', 'were', 'an', 'untidy', 'devil', '.', 'de', 'Reves', ':', 'Well', ',', 'what', 'do', 'you', 'make', 'of', 'it', '?', 'Prattle', ':', 'It', 'reminds', 'me', 'of', 'your', 'room', 'at', 'Eton', '.', 'de', 'Reves', ':', 'My', 'room', 'at', 'Eton', '?', 'Prattle', ':', 'Yes', ',', 'you', 'always', 'had', 'papers', 'all', 'over', 'your', 'floor', '.', 'de', 'Reves', ':', 'Oh', ',', 'yes', '-', '-', 'Prattle', ':', 'And', 'what', 'are', 'these', '?', 'de', 'Reves', ':', 'All', 'these', 'are', 'poems', ';', 'and', 'this', 'is', 'my', 'altar', 'to', 'Fame', '.', 'Prattle', ':', 'To', 'Fame', '?', 'de', 'Reves', ':', 'The', 'same', 'that', 'Homer', 'knew', '.', 'Prattle', ':', 'Good', 'Lord', '!', 'de', 'Reves', ':', 'Keats', 'never', 'saw', 'her', '.', 'Shelley', 'died', 'too', 'young', '.', 'She', 'came', 'late', 'at', 'the', 'best', 'of', 'times', ',', 'now', 'scarcely', 'ever', '.', 'Prattle', ':', 'But', ',', 'my', 'dear', 'fellow', ',', 'you', 'do', "n't", 'mean', 'that', 'you', 'think', 'there', 'really', 'is', 'such', 'a', 'person', '?', 'de', 'Reves', ':', 'I', 'offer', 'all', 'my', 'songs', 'to', 'her', '.', 'Prattle', ':', 'But', 'you', 'do', "n't", 'mean', 'you', 'think', 'you', 'could', 'actually', 'see', 'Fame', '?', 'de', 'Reves', ':', 'We', 'poets', 'personify', 'abstract', 'things', ',', 'and', 'not', 'poets', 'only', 'but', 'sculptors7', 'and', 'painters', 'too', '.', 'All', 'the', 'great', 'things', 'of', 'the', 'world', 'are', 'those', 'abstract', 'things', '.', 'Prattle', ':', 'But', 'what', 'I', 'mean', 'is', ',', 'they', "'re", 'not', 'really', 'there', ',', 'like', 'you', 'or', 'me', '.', 'de', 'Reves', ':', 'To', 'us', 'these', 'things', 'are', 'more', 'real', 'than', 'men', ',', 'they', 'outlive', 'generations', ',', 'they', 'watch', 'the', 'passing', 'of', 'kingdoms', ':', 'we', 'go', 'by', 'them', 'like', 'dust', ';', 'they', 'are', 'still', 'there', ',', 'unmoved', ',', 'unsmiling', '.', 'Prattle', ':', 'But', ',', 'but', ',', 'you', 'ca', "n't", 'think', 'that', 'you', 'could', 'see', 'Fame', ',', 'you', 'do', "n't", 'expect', 'to', 'see', 'it', '?', 'de', 'Reves', ':', 'Not', 'to', 'me', '.', 'Never', 'to', 'me', '.', 'She', 'of', 'the', 'golden', 'trumpet', 'and', 'Greek', 'dress', 'will', 'never', 'appear', 'to', 'me', '...', 'We', 'all', 'have', 'our', 'dreams', '.', 'Prattle', ':', 'I', 'say', '-', 'what', 'have', 'you', 'been', 'doing', 'all', 'day', '?', 'de', 'Reves', ':', 'I', '?', 'Oh', ',', 'only', 'writing', 'a', 'sonnet', '.', 'Prattle', ':', 'Is', 'it', 'a', 'long', 'one', '?', 'de', 'Reves', ':', 'Not', 'very', '.', 'Prattle', ':', 'About', 'how', 'long', 'is', 'it', '?', 'de', 'Reves', ':', 'About', 'fourteen', 'lines', '.', 'Prattle', '(', 'impressively', ')', ':', 'I', 'tell', 'you', 'what', 'it', 'is', '.', 'de', 'Reves', ':', 'Yes', '?', 'Prattle', ':', 'I', 'tell', 'you', 'what', '.', 'You', "'ve", 'been', 'overworking', 'yourself', '.', 'I', 'once', 'got', 'like', 'that', 'on', 'board', 'the', 'Sandhurst', ',', 'working', 'for', 'the', 'passing-out', 'exam', '.', 'I', 'got', 'so', 'bad', 'that', 'I', 'could', 'have', 'seen', 'anything', '.', 'de', 'Reves', ':', 'Seen', 'anything', '?', 'Prattle', ':', 'Lord', ',', 'yes', ';', 'horned', 'pigs', ',', 'snakes', 'with', 'wings', ';', 'anything', ';', 'one', 'of', 'your', 'winged', 'horses', 'even', '.', 'They', 'gave', 'me', 'some', 'stuff', 'called', 'bromide', 'for', 'it', '.', 'You', 'take', 'a', 'rest', '.', 'de', 'Reves', ':', 'But', 'my', 'dear', 'fellow', ',', 'you', 'do', "n't", 'understand', 'at', 'all', '.', 'I', 'merely', 'said', 'that', 'abstract', 'things', 'are', 'to', 'a', 'poet', 'as', 'near', 'and', 'real', 'and', 'visible', 'as', 'one', 'of', 'your', 'bookmakers', 'or', 'barmaids', '.', 'Prattle', ':', 'I', 'know', '.', 'You', 'take', 'a', 'rest', '.', 'de', 'Reves', ':', 'Well', ',', 'perhaps', 'I', 'will', '.', 'I', "'d", 'come', 'with', 'you', 'to', 'that', 'musical', 'comedy', 'you', "'re", 'going', 'to', 'see', ',', 'only', 'I', "'m", 'a', 'bit', 'tired', 'after', 'writing', 'this', ';', 'it', "'s", 'a', 'tedious', 'job', '.', 'I', "'ll", 'come', 'another', 'night', '.', 'Prattle', ':', 'How', 'do', 'you', 'know', 'I', "'m", 'going', 'to', 'see', 'a', 'musical', 'comedy', '?', 'de', 'Reves', ':', 'Well', ',', 'where', 'would', 'you', 'go', '?', 'Hamlet', "'s", '8', 'on', 'at', 'the', 'Lord', 'Chamberlain', "'s", '.', 'You', "'re", 'not', 'going', 'there', '.', 'Prattle', ':', 'Do', 'I', 'look', 'like', 'it', '?', 'de', 'Reves', ':', 'No', '.', 'Prattle', ':', 'Well', ',', 'you', "'re", 'quite', 'right', '.', 'I', "'m", 'going', 'to', 'see', '``', 'The', 'Girl', 'from', 'Bedlam', '.', "''", 'So', 'long', '.', 'I', 'must', 'push', 'off', 'now', '.', 'It', "'s", 'getting', 'late', '.', 'You', 'take', 'a', 'rest', '.', 'Do', "n't", 'add', 'another', 'line', 'to', 'that', 'sonnet', ';', 'fourteen', "'s", 'quite', 'enough', '.', 'You', 'take', 'a', 'rest', '.', 'Do', "n't", 'have', 'any', 'dinner', 'to-night', ',', 'just', 'rest', '.', 'I', 'was', 'like', 'that', 'once', 'myself', '.', 'So', 'long', '.', 'de', 'Reves', ':', 'So', 'long', '.', '[', 'Exit', 'Prattle', '.', 'de', 'Reves', 'returns', 'to', 'his', 'table', 'and', 'sits', 'down', '.', 'Good', 'old', 'Dick', '!', 'He', "'s", 'the', 'same', 'as', 'ever', '.', 'Lord', ',', 'how', 'time', 'passes', '.', 'He', 'takes', 'his', 'pen', 'and', 'his', 'sonnet', 'and', 'makes', 'a', 'few', 'alterations', '.', 'Well', ',', 'that', "'s", 'finished', '.', 'I', 'ca', "n't", 'do', 'any', 'more', 'to', 'it', '.', '[', 'He', 'rises', 'and', 'goes', 'to', 'the', 'screen', ';', 'he', 'draws', 'back', 'part', 'of', 'it', 'and', 'goes', 'up', 'to', 'the', 'altar', '.', 'He', 'is', 'about', 'to', 'place', 'his', 'sonnet', 'reverently', 'at', 'the', 'foot', 'of', 'the', 'altar', 'amongst', 'his', 'other', 'verses', '.', 'No', ',', 'I', 'will', 'not', 'put', 'it', 'there', '.', 'This', 'one', 'is', 'worthy', 'of', 'the', 'altar', '.', '[', 'He', 'places', 'the', 'sonnet', 'upon', 'the', 'altar', 'itself', '.', 'If', 'that', 'sonnet', 'does', 'not', 'give', 'me', 'fame', ',', 'nothing', 'that', 'I', 'have', 'done', 'before', 'will', 'give', 'it', 'to', 'me', ',', 'nothing', 'that', 'I', 'ever', 'will', 'do', '.', '[', 'He', 'replaces', 'the', 'screen', 'and', 'returns', 'to', 'his', 'chair', 'at', 'the', 'table', '.', 'Twilight', 'is', 'coming', 'on', '.', 'He', 'sits', 'with', 'his', 'elbow', 'on', 'the', 'table', ',', 'his', 'head', 'on', 'his', 'hand', ',', 'or', 'however', 'the', 'actor', 'pleases', '.', 'Well', ',', 'well', '.', 'Fancy', 'seeing', 'Dick', 'again', '.', 'Well', ',', 'Dick', 'enjoys', 'his', 'life', ',', 'so', 'he', "'s", 'no', 'fool', '.', 'What', 'was', 'that', 'he', 'said', '?', '``', 'There', "'s", 'no', 'money', 'in', 'poetry', '.', 'You', "'d", 'better', 'chuck', 'it', '.', "''", 'Ten', 'years', "'", 'work', 'and', 'what', 'have', 'I', 'to', 'show', 'for', 'it', '?', 'The', 'admiration', 'of', 'men', 'who', 'care', 'for', 'poetry', ',', 'and', 'how', 'many', 'of', 'them', 'are', 'there', '?', 'There', "'s", 'a', 'bigger', 'demand', 'for', 'smoked', 'glasses', 'to', 'look', 'at', 'eclipses', 'of', 'the', 'sun', '.', 'Why', 'should', 'Fame', 'come', 'to', 'me', '?', 'Have', "n't", 'I', 'given', 'up', 'my', 'days', 'for', 'her', '?', 'That', 'is', 'enough', 'to', 'keep', 'her', 'away', '.', 'I', 'am', 'a', 'poet', ';', 'that', 'is', 'enough', 'reason', 'for', 'her', 'to', 'slight', 'me', '.', 'Proud', 'and', 'aloof', 'and', 'cold', 'as', 'marble', ',', 'what', 'does', 'Fame', 'care', 'for', 'us', '?', 'Yes', ',', 'Dick', 'is', 'right', '.', 'It', "'s", 'a', 'poor', 'game', 'chasing', 'illusions', ',', 'hunting', 'the', 'intangible', ',', 'pursuing', 'dreams', '.', 'Dreams', '?', 'Why', ',', 'we', 'are', 'ourselves', 'dreams', '.', '[', 'He', 'leans', 'back', 'in', 'his', 'chair', '.', 'We', 'are', 'such', 'stuff', 'As', 'dreams', 'are', 'made', 'on', ',', 'and', 'our', 'little', 'life', 'Is', 'rounded', 'with', 'a', 'sleep', '.', '[', 'He', 'is', 'silent', 'for', 'a', 'while', '.', 'Suddenly', 'he', 'lifts', 'his', 'head', '.', 'My', 'room', 'at', 'Eton', ',', 'Dick', 'said', '.', 'An', 'untidy', 'mess', '.', '[', 'As', 'he', 'lifts', 'his', 'head', 'and', 'says', 'these', 'words', ',', 'twilight', 'gives', 'place', 'to', 'broad', 'daylight', ',', 'merely', 'as', 'a', 'hint', 'that', 'the', 'author', 'of', 'the', 'play', 'may', 'have', 'been', 'mistaken', ',', 'and', 'the', 'whole', 'thing', 'may', 'have', 'been', 'no', 'more', 'than', 'a', 'poet', "'s", 'dream', '.', 'So', 'it', 'was', ',', 'and', 'it', "'s", 'an', 'untidy', 'mess', 'there', '(', 'looking', 'at', 'screen', ')', 'too', '.', 'Dick', "'s", 'right', '.', 'I', "'ll", 'tidy', 'it', 'up', '.', 'I', "'ll", 'burn', 'the', 'whole', 'damned', 'heap', ',', '[', 'He', 'advances', 'impetuously', 'towards', 'the', 'screen', '.', 'every', 'damned', 'poem', 'that', 'I', 'was', 'ever', 'fool', 'enough', 'to', 'waste', 'my', 'time', 'on', '.', '[', 'He', 'pushes', 'back', 'the', 'screen', '.', 'Fame', 'in', 'a', 'Greek', 'dress', 'with', 'a', 'long', 'golden', 'trumpet', 'in', 'her', 'hand', 'is', 'seen', 'standing', 'motionless', 'on', 'the', 'altar', 'like', 'a', 'marble', 'goddess', '.', 'So', '...', 'you', 'have', 'come', '!', '[', 'For', 'a', 'while', 'he', 'stands', 'thunderstruck', '.', 'Then', 'he', 'approaches', 'the', 'altar', '.', 'Divine', 'fair', 'lady', ',', 'you', 'have', 'come', '.', '[', 'He', 'holds', 'up', 'his', 'hand', 'to', 'her', 'and', 'leads', 'her', 'down', 'from', 'the', 'altar', 'and', 'into', 'the', 'centre', 'of', 'the', 'stage', '.', 'At', 'whatever', 'moment', 'the', 'actor', 'finds', 'it', 'most', 'convenient', ',', 'he', 'repossesses', 'himself', 'of', 'the', 'sonnet', 'that', 'he', 'had', 'placed', 'on', 'the', 'altar', '.', 'He', 'now', 'offers', 'it', 'to', 'Fame', '.', 'This', 'is', 'my', 'sonnet', '.', 'Is', 'it', 'well', 'done', '?', '[', 'Fame', 'takes', 'it', 'and', 'reads', 'it', 'in', 'silence', ',', 'while', 'the', 'Poet', 'watches', 'her', 'rapturously', '.', 'Fame', ':', 'You', "'re", 'a', 'bit', 'of', 'all', 'right', '.', 'de', 'Reves', ':', 'What', '?', 'Fame', ':', 'Some', 'poet', '.', 'de', 'Reves', ':', 'I', '-', 'I', '-', 'scarcely', '...', 'understand', '.', 'Fame', ':', 'You', "'re", 'IT', '.', 'de', 'Reves', ':', 'But', '...', 'it', 'is', 'not', 'possible', '...', 'are', 'you', 'she', 'that', 'knew', 'Homer', '?', 'Fame', ':', 'Homer', '?', 'Lord', ',', 'yes', '.', 'Blind', 'old', 'bat', ',', "'", 'e', 'could', "n't", 'see', 'a', 'yard', '.', 'de', 'Reves', ':', 'O', 'Heavens', '!', '[', 'Fame', 'walks', 'beautifully', 'to', 'the', 'window', '.', 'She', 'opens', 'it', 'and', 'puts', 'her', 'head', 'out', '.', 'Fame', '(', 'in', 'a', 'voice', 'with', 'which', 'a', 'woman', 'in', 'an', 'upper', 'storey', 'would', 'cry', 'for', 'help', 'if', 'the', 'house', 'was', 'well', 'alight', ')', ':', 'Hi', '!', 'Hi', '!', 'Boys', '!', 'Hi', '!', 'Say', ',', 'folks', '!', 'Hi', '!', '[', 'The', 'murmur', 'of', 'a', 'gathering', 'crowd', 'is', 'heard', '.', 'Fame', 'blows', 'her', 'trumpet', '.', 'Fame', ':', 'Hi', ',', 'he', "'s", 'a', 'poet', '!', '(', 'Quickly', ',', 'over', 'her', 'shoulder', '.', ')', 'What', "'s", 'your', 'name', '?', 'de', 'Reves', ':', 'De', 'Reves', '.', 'Fame', ':', 'His', 'name', "'s", 'de', 'Reves', '.', 'de', 'Reves', ':', 'Harry', 'de', 'Reves', '.', 'Fame', ':', 'His', 'pals', 'call', 'him', 'Harry', '.', 'The', 'Crowd', ':', 'Hooray', '!', 'Hooray', '!', 'Hooray', '!', 'Fame', ':', 'Say', ',', 'what', "'s", 'your', 'favourite', 'colour', '?', 'de', 'Reves', ':', 'I', '...', 'I', '...', 'I', 'do', "n't", 'quite', 'understand', '.', 'Fame', ':', 'Well', ',', 'which', 'do', 'you', 'like', 'best', ',', 'green', 'or', 'blue', '?', 'de', 'Reves', ':', 'Oh', '-', 'er', '-', 'blue', '.', '[', 'She', 'blows', 'her', 'trumpet', 'out', 'of', 'the', 'window', '.', 'No', '-', 'er', '-', 'I', 'think', 'green', '.', 'Fame', ':', 'Green', 'is', 'his', 'favourite', 'colour', '.', 'The', 'Crowd', ':', 'Hooray', '!', 'Hooray', '!', 'Hooray', '!', 'Fame', ':', '`', 'Ere', ',', 'tell', 'us', 'something', '.', 'They', 'want', 'to', 'know', 'all', 'about', 'yer', '.', 'de', 'Reves', ':', 'Would', "n't", '9', 'you', 'perhaps', '...', 'would', 'they', 'care', 'to', 'hear', 'my', 'sonnet', ',', 'if', 'you', 'would', '-', 'er', '...', 'Fame', '(', 'picking', 'up', 'quill', ')', ':', 'Here', ',', 'what', "'s", 'this', '?', 'de', 'Reves', ':', 'Oh', ',', 'that', "'s", 'my', 'pen', '.', 'Fame', '(', 'after', 'another', 'blast', 'on', 'her', 'trumpet', ')', ':', 'He', 'writes', 'with', 'a', 'quill', '.', '[', 'Cheers', 'from', 'the', 'Crowd', '.', 'Fame', '(', 'going', 'to', 'a', 'cupboard', ')', ':', 'Here', ',', 'what', 'have', 'you', 'got', 'in', 'here', '?', 'de', 'Reves', ':', 'Oh', '...', 'er', '...', 'those', 'are', 'my', 'breakfast', 'things', '.', 'Fame', '(', 'finding', 'a', 'dirty', 'plate', ')', ':', 'What', 'have', 'yer', 'had', 'on', 'this', 'one', '?', 'de', 'Reves', '(', 'mournfully', ')', ':', 'Oh', ',', 'eggs', 'and', 'bacon', '.', 'Fame', '(', 'at', 'the', 'window', ')', ':', 'He', 'has', 'eggs', 'and', 'bacon', 'for', 'breakfast', '.', 'The', 'Crowd', ':', 'Hip', 'hip', 'hip', ',', 'hooray', '!', 'Hip', 'hip', 'hip', ',', 'hooray', '!', 'Hip', 'hip', 'hip', ',', 'hooray', '!', 'Fame', ':', 'Hi', ',', 'and', 'what', "'s", 'this', '?', 'de', 'Reves', '(', 'miserably', ')', ':', 'Oh', ',', 'a', 'golf', 'stick', '.', 'Fame', ':', 'He', "'s", 'a', 'man', "'s", 'man', '!', 'He', "'s", 'a', 'virile', 'man', '!', 'He', "'s", 'a', 'manly', 'man', '!', '[', 'Wild', 'cheers', 'from', 'the', 'Crowd', ',', 'this', 'time', 'only', 'from', 'women', "'s", 'voices', '.', 'de', 'Reves', ':', 'Oh', ',', 'this', 'is', 'terrible', '.', 'This', 'is', 'terrible', '.', 'This', 'is', 'terrible', '.', '[', 'Fame', 'gives', 'another', 'peal', 'on', 'her', 'horn', '.', 'She', 'is', 'about', 'to', 'speak', '.', 'de', 'Reves', '(', 'solemnly', 'and', 'mournfully', ')', ':', 'One', 'moment', ',', 'one', 'moment', '...', 'Fame', ':', 'Well', ',', 'out', 'with', 'it', '.', 'de', 'Reves', ':', 'For', 'ten', 'years', ',', 'divine', 'lady', ',', 'I', 'have', 'worshipped', 'you', ',', 'offering', 'all', 'my', 'songs', '...', 'I', 'find', '...', 'I', 'find', 'I', 'am', 'not', 'worthy', '...', 'Fame', ':', 'Oh', ',', 'you', "'re", 'all', 'right', '.', 'de', 'Reves', ':', 'No', ',', 'no', ',', 'I', 'am', 'not', 'worthy', '.', 'It', 'can', 'not', 'be', '.', 'It', 'can', 'not', 'possibly', 'be', '.', 'Others', 'deserve', 'you', 'more', '.', 'I', 'must', 'say', 'it', '!', 'I', 'can', 'not', 'possibly', 'love', 'you', '.', 'Others', 'are', 'worthy', '.', 'You', 'will', 'find', 'others', '.', 'But', 'I', ',', 'no', ',', 'no', ',', 'no', '.', 'It', 'can', 'not', 'be', '.', 'It', 'can', 'not', 'be', '.', 'Oh', ',', 'pardon', 'me', ',', 'but', 'it', 'must', 'not', '.', '[', 'Meanwhile', 'Fame', 'has', 'been', 'lighting', 'one', 'of', 'his', 'cigarettes', '.', 'She', 'sits', 'in', 'a', 'comfortable', 'chair', ',', 'leans', 'right', 'back', ',', 'and', 'puts', 'her', 'feet', 'right', 'up', 'on', 'the', 'table', 'amongst', 'the', 'poet', "'s", 'papers', '.', 'Oh', ',', 'I', 'fear', 'I', 'offend', 'you', '.', 'But', '-', 'it', 'can', 'not', 'be', '.', 'Fame', ':', 'Oh', ',', 'that', "'s", 'all', 'right', ',', 'old', 'bird', ';', 'no', 'offence', '.', 'I', 'ai', "n't", 'going', 'to', 'leave', 'you', '.', 'de', 'Reves', ':', 'But', '-', 'but', '-', 'but', '-', 'I', 'do', 'not', 'understand', '.', 'Fame', ':', 'I', "'ve", 'come', 'to', 'stay', ',', 'I', 'have', '.', '[', 'She', 'blows', 'a', 'puff', 'of', 'smoke', 'through', 'her', 'trumpet', '.', 'CURTAIN', '.'], 'pos_tags': [10, 0, 2, 12, 12, 12, 12, 12, 12, 38, 2, 12, 38, 41, 2, 10, 38, 18, 5, 10, 5, 6, 10, 38, 30, 29, 29, 0, 30, 6, 12, 12, 38, 42, 12, 12, 38, 2, 12, 5, 2, 12, 12, 13, 38, 12, 38, 10, 2, 12, 15, 11, 5, 12, 38, 11, 5, 18, 38, 2, 6, 10, 5, 2, 10, 38, 10, 38, 12, 6, 38, 2, 12, 30, 28, 5, 2, 10, 10, 38, 41, 12, 12, 12, 38, 10, 38, 12, 38, 12, 38, 12, 12, 38, 12, 38, 12, 38, 6, 12, 38, 35, 31, 16, 5, 22, 10, 41, 18, 42, 38, 2, 11, 5, 2, 10, 38, 12, 12, 38, 25, 38, 16, 31, 29, 22, 10, 38, 27, 16, 9, 26, 21, 0, 26, 35, 16, 27, 28, 5, 38, 12, 12, 38, 25, 38, 32, 30, 6, 38, 33, 31, 16, 28, 5, 12, 22, 10, 38, 18, 38, 16, 27, 24, 26, 5, 16, 9, 26, 1, 0, 1, 6, 11, 24, 26, 38, 16, 9, 26, 10, 21, 18, 38, 18, 16, 27, 16, 9, 26, 2, 10, 0, 26, 35, 12, 27, 28, 5, 38, 12, 12, 38, 6, 22, 35, 30, 10, 22, 10, 38, 2, 28, 6, 38, 12, 12, 38, 32, 30, 6, 38, 10, 41, 28, 10, 0, 10, 42, 38, 0, 33, 31, 16, 28, 22, 12, 12, 38, 28, 38, 10, 38, 28, 22, 16, 27, 36, 26, 16, 27, 38, 12, 12, 38, 25, 38, 16, 31, 29, 24, 16, 18, 38, 10, 38, 16, 31, 38, 28, 30, 18, 6, 38, 33, 31, 16, 26, 22, 12, 12, 38, 25, 38, 10, 38, 10, 38, 10, 22, 6, 12, 22, 12, 12, 38, 25, 38, 2, 10, 5, 10, 38, 16, 31, 38, 10, 38, 6, 12, 22, 26, 16, 26, 2, 10, 5, 16, 22, 12, 12, 38, 25, 38, 18, 18, 38, 10, 38, 16, 31, 38, 35, 31, 36, 16, 31, 16, 22, 12, 12, 38, 25, 38, 16, 31, 36, 26, 38, 2, 11, 31, 24, 26, 17, 10, 38, 18, 38, 2, 30, 35, 16, 31, 5, 38, 10, 38, 16, 9, 26, 16, 5, 3, 30, 2, 10, 5, 16, 38, 12, 12, 38, 25, 38, 0, 18, 16, 30, 18, 5, 17, 10, 38, 30, 16, 22, 16, 9, 18, 26, 5, 10, 5, 3, 27, 10, 5, 16, 38, 10, 38, 25, 38, 16, 31, 36, 26, 2, 38, 5, 16, 9, 26, 18, 18, 5, 10, 5, 16, 31, 5, 28, 16, 31, 36, 26, 16, 9, 36, 26, 2, 10, 10, 38, 18, 38, 38, 12, 12, 38, 18, 33, 22, 10, 38, 25, 38, 16, 31, 36, 26, 38, 18, 3, 30, 7, 10, 5, 28, 38, 18, 38, 12, 12, 38, 25, 38, 25, 38, 16, 31, 16, 30, 7, 24, 26, 33, 2, 6, 10, 30, 28, 24, 26, 38, 5, 24, 26, 33, 12, 38, 38, 10, 38, 33, 30, 12, 22, 12, 12, 38, 25, 38, 2, 29, 10, 5, 11, 38, 10, 38, 16, 31, 22, 16, 31, 36, 26, 5, 2, 29, 10, 38, 31, 16, 22, 12, 12, 38, 5, 17, 10, 16, 31, 5, 2, 6, 11, 38, 16, 18, 31, 2, 6, 10, 24, 16, 38, 2, 10, 5, 12, 30, 18, 6, 2, 10, 24, 2, 10, 5, 2, 12, 10, 9, 26, 24, 16, 38, 10, 38, 16, 31, 38, 41, 26, 16, 2, 10, 38, 11, 38, 42, 33, 22, 18, 16, 9, 26, 5, 11, 0, 11, 38, 0, 12, 38, 0, 14, 2, 10, 5, 11, 22, 12, 12, 38, 25, 38, 25, 38, 5, 2, 5, 16, 38, 10, 38, 6, 12, 22, 12, 12, 38, 16, 31, 5, 2, 12, 12, 5, 12, 38, 31, 36, 16, 22, 10, 38, 25, 38, 5, 10, 38, 0, 33, 30, 38, 38, 12, 12, 38, 1, 1, 11, 0, 18, 27, 16, 12, 12, 38, 27, 36, 16, 22, 0, 16, 30, 24, 16, 2, 10, 0, 10, 0, 10, 5, 38, 38, 10, 38, 25, 38, 0, 38, 16, 31, 38, 33, 30, 14, 2, 38, 38, 12, 12, 38, 25, 38, 16, 30, 5, 2, 10, 24, 16, 38, 0, 16, 27, 16, 12, 12, 38, 0, 18, 16, 30, 1, -1, 10, 38, 18, 38, 5, 10, 16, 30, 38, 12, 12, 38, 5, 2, 6, 10, 12, 30, 29, 29, 33, 16, 30, 5, 11, 38, 5, 11, 24, 33, 16, 30, 6, 11, 38, 10, 41, 28, 5, 17, 10, 0, 28, 18, 38, 28, 0, 28, 5, 2, 12, 5, 2, 10, 5, 6, 10, 42, 38, 16, 31, -1, 16, 31, -1, 16, 6, 11, -1, 0, 12, 12, -1, 41, 16, 30, 5, 2, 6, 10, 18, 38, 28, 16, 18, 2, 6, 38, 12, 12, 38, 31, 21, 22, 26, 21, 22, 10, 38, 33, 22, 33, 30, 2, 10, 22, 12, 12, 38, 2, 10, 22, 10, 38, 25, 38, 18, 38, 25, 38, 16, 9, 26, 16, 18, 38, 41, 16, 30, 18, 24, 26, 10, 5, 16, 38, 12, 12, 38, 25, 38, 31, 36, 26, 10, 18, 38, 10, 38, 33, 22, 35, 36, 22, 12, 12, 38, 25, 38, 16, 9, 36, 26, 38, 10, 38, 9, 36, 26, 22, 35, 38, 33, 31, 16, 27, 22, 12, 12, 38, 25, 38, 1, 5, 2, 11, -1, 16, 9, 36, 26, 38, 10, 38, 5, 10, 16, 9, 26, 38, 26, 30, 26, 2, 10, 38, 41, 12, 12, 30, 5, 12, 0, 2, 10, 38, 16, 30, 18, 7, 38, 10, 11, 31, 2, 10, 5, 2, 10, 38, 2, 10, 38, 12, 12, 41, 28, 2, 10, 18, 42, 38, 32, 30, 18, 38, 33, 31, 16, 26, 5, 16, 22, 41, 2, 10, 5, 6, 10, 38, 29, 5, 2, 10, 38, 30, 29, 38, 11, 31, 2, 10, 18, 5, 16, 38, 10, 38, 16, 31, 38, 16, 18, 27, 2, 6, 10, 38, 12, 12, 38, 25, 38, 33, 31, 16, 26, 5, 16, 22, 10, 38, 16, 30, 16, 5, 17, 10, 5, 12, 38, 12, 12, 38, 17, 10, 5, 12, 22, 10, 38, 25, 38, 16, 18, 27, 11, 18, 5, 17, 10, 38, 12, 12, 38, 25, 38, 25, 38, 38, 10, 38, 0, 33, 31, 2, 22, 12, 12, 38, 14, 2, 31, 11, 38, 0, 2, 30, 17, 10, 24, 12, 38, 10, 38, 24, 12, 22, 12, 12, 38, 2, 6, 5, 12, 27, 38, 10, 38, 6, 12, 22, 12, 12, 38, 12, 18, 27, 16, 38, 12, 27, 18, 6, 38, 16, 27, 18, 5, 2, 8, 5, 11, 38, 18, 18, 18, 38, 10, 38, 0, 38, 17, 6, 10, 38, 16, 31, 36, 26, 5, 16, 31, 3, 18, 30, 14, 2, 10, 22, 12, 12, 38, 16, 31, 14, 17, 11, 24, 16, 38, 10, 38, 0, 16, 31, 36, 26, 16, 31, 16, 9, 18, 26, 12, 22, 12, 12, 38, 16, 11, 31, 6, 11, 38, 0, 36, 11, 6, 0, 6, 0, 11, 18, 38, 14, 2, 6, 11, 5, 2, 10, 31, 2, 6, 11, 38, 10, 38, 0, 33, 16, 31, 30, 38, 16, 31, 36, 18, 18, 38, 5, 16, 0, 16, 38, 12, 12, 38, 24, 16, 2, 11, 31, 19, 6, 5, 11, 38, 16, 31, 11, 38, 16, 31, 2, 10, 5, 11, 38, 16, 31, 5, 16, 31, 10, 38, 16, 31, 18, 18, 38, 6, 38, 12, 38, 10, 38, 0, 38, 18, 38, 16, 9, 36, 26, 5, 16, 9, 26, 12, 38, 16, 31, 36, 26, 24, 26, 16, 22, 12, 12, 38, 36, 24, 16, 38, 18, 24, 16, 38, 16, 5, 2, 6, 10, 0, 6, 10, 9, 18, 26, 24, 16, -1, 16, 18, 31, 17, 11, 38, 10, 38, 16, 31, 38, 33, 31, 16, 29, 28, 2, 10, 22, 12, 12, 38, 16, 22, 25, 38, 18, 28, 2, 10, 38, 10, 38, 30, 16, 2, 6, 1, 22, 12, 12, 38, 36, 18, 38, 10, 38, 18, 35, 18, 30, 16, 22, 12, 12, 38, 5, 10, 11, 38, 10, 41, 18, 42, 38, 16, 26, 16, 33, 16, 30, 38, 12, 12, 38, 25, 22, 10, 38, 16, 26, 16, 33, 38, 16, 31, 29, 28, 16, 38, 16, 18, 27, 5, 5, 5, 10, 2, 12, 38, 28, 5, 2, 6, 10, 38, 16, 27, 18, 6, 5, 16, 9, 26, 29, 10, 38, 12, 12, 38, 29, 10, 22, 10, 38, 12, 38, 25, 38, 29, 11, 38, 11, 5, 11, 38, 10, 38, 1, 5, 17, 29, 11, 18, 38, 16, 27, 16, 2, 10, 27, 10, 5, 16, 38, 16, 31, 2, 10, 38, 12, 12, 38, 0, 17, 6, 10, 38, 16, 31, 36, 26, 5, 2, 38, 16, 18, 27, 5, 6, 11, 31, 24, 2, 10, 5, 6, 0, 6, 0, 6, 5, 1, 5, 17, 11, 0, 11, 38, 10, 38, 16, 31, 38, 16, 31, 2, 10, 38, 12, 12, 38, 25, 38, 18, 16, 9, 38, 16, 9, 26, 5, 16, 24, 2, 6, 10, 16, 31, 28, 24, 26, 38, 18, 16, 31, 2, 10, 29, 5, 28, 2, 38, 16, 30, 2, 6, 10, 38, 16, 9, 26, 2, 10, 38, 10, 38, 35, 31, 16, 31, 16, 31, 28, 24, 26, 2, 6, 10, 22, 12, 12, 38, 25, 38, 35, 9, 16, 26, 22, 12, 30, 1, 5, 5, 2, 12, 12, 15, 38, 16, 31, 36, 28, 18, 38, 10, 38, 31, 16, 31, 5, 16, 22, 12, 12, 38, 25, 38, 10, 38, 18, 38, 16, 31, 18, 6, 38, 16, 31, 28, 24, 26, 39, 2, 12, 5, 12, 38, 40, 18, 18, 38, 16, 9, 26, 21, 18, 38, 16, 30, 28, 18, 38, 16, 31, 2, 10, 38, 31, 36, 26, 2, 10, 24, 2, 10, 38, 10, 30, 18, 6, 38, 16, 31, 2, 10, 38, 31, 36, 26, 2, 10, 10, 38, 18, 10, 38, 16, 27, 6, 5, 5, 16, 38, 18, 18, 38, 12, 12, 38, 18, 18, 38, 41, 10, 12, 38, 12, 12, 30, 24, 17, 10, 0, 30, 21, 38, 6, 6, 12, 22, 16, 30, 2, 6, 18, 18, 38, 12, 38, 35, 10, 30, 38, 16, 30, 17, 10, 0, 17, 10, 0, 30, 2, 6, 11, 38, 18, 38, 32, 30, 29, 38, 16, 9, 36, 26, 2, 19, 24, 16, 38, 41, 16, 30, 0, 30, 24, 2, 10, 38, 16, 30, 18, 10, 5, 16, 0, 30, 21, 24, 2, 10, 38, 16, 30, 18, 24, 26, 17, 10, 18, 5, 2, 10, 5, 2, 10, 5, 17, 6, 11, 38, 25, 38, 16, 9, 36, 26, 16, 18, 38, 2, 1, 30, 6, 5, 2, 10, 38, 41, 16, 30, 2, 10, 5, 2, 10, 16, 38, 5, 2, 10, 30, 36, 26, 16, 10, 38, 10, 5, 16, 31, 29, 18, 9, 26, 16, 24, 16, 38, 10, 5, 16, 18, 9, 26, 38, 41, 16, 30, 2, 10, 0, 11, 24, 17, 10, 5, 2, 10, 38, 10, 30, 28, 21, 38, 16, 30, 5, 17, 10, 5, 2, 10, 38, 17, 10, 5, 17, 10, 38, 0, 18, 2, 10, 30, 38, 25, 38, 25, 38, 6, 28, 12, 18, 38, 18, 38, 12, 30, 17, 10, 38, 18, 16, 30, 2, 10, 38, 33, 27, 5, 16, 27, 22, 39, 3, 30, 2, 10, 5, 10, 38, 16, 9, 19, 26, 16, 38, 40, 1, 11, 15, 10, 0, 33, 31, 16, 24, 26, 5, 16, 22, 2, 10, 5, 11, 33, 31, 5, 10, 38, 0, 35, 6, 5, 16, 31, 18, 22, 3, 30, 2, 7, 10, 5, 29, 11, 24, 26, 5, 11, 5, 2, 10, 38, 35, 9, 12, 26, 24, 16, 22, 31, 36, 16, 29, 21, 17, 11, 5, 16, 22, 2, 30, 6, 24, 26, 16, 21, 38, 16, 31, 2, 10, 38, 32, 30, 18, 10, 5, 16, 24, 26, 16, 38, 6, 0, 6, 0, 6, 5, 10, 38, 33, 30, 12, 10, 5, 16, 22, 25, 38, 12, 30, 6, 38, 16, 30, 2, 6, 10, 28, 11, 38, 28, 2, 10, 38, 28, 11, 38, 11, 22, 35, 38, 16, 31, 16, 30, 38, 41, 16, 30, 18, 5, 17, 10, 38, 16, 31, 6, 10, 5, 11, 31, 29, 5, 38, 0, 17, 6, 10, 30, 29, 5, 2, 10, 38, 41, 16, 30, 6, 5, 2, 10, 38, 18, 16, 30, 17, 10, 38, 17, 10, 5, 12, 38, 12, 27, 38, 2, 6, 10, 38, 41, 5, 16, 30, 17, 10, 0, 30, 2, 11, 38, 10, 30, 10, 24, 6, 10, 38, 18, 5, 2, 10, 5, 2, 10, 5, 2, 10, 9, 26, 29, 29, 38, 0, 2, 6, 10, 9, 26, 29, 18, 7, 5, 2, 10, 15, 10, 38, 18, 16, 27, 38, 0, 16, 30, 2, 6, 10, 18, 41, 28, 5, 10, 42, 18, 38, 12, 15, 10, 38, 16, 9, 26, 16, 21, 38, 16, 9, 26, 2, 6, 6, 10, 38, 41, 16, 30, 18, 5, 2, 10, 38, 2, 6, 10, 5, 16, 27, 18, 6, 18, 24, 26, 17, 10, 21, 38, 41, 16, 30, 18, 2, 10, 38, 10, 5, 2, 6, 10, 5, 2, 6, 6, 10, 5, 17, 10, 30, 29, 28, 6, 5, 2, 10, 5, 2, 10, 10, 38, 18, -1, 16, 31, 29, 22, 41, 5, 2, 5, 16, 30, 6, 38, 18, 16, 30, 2, 10, 38, 12, 6, 10, 38, 16, 31, 29, 38, 41, 16, 30, 21, 17, 10, 24, 16, 0, 30, 16, 21, 5, 2, 10, 0, 5, 2, 10, 5, 2, 10, 38, 5, 32, 10, 2, 10, 30, 16, 20, 6, 38, 16, 30, 16, 5, 2, 10, 5, 16, 27, 29, 5, 2, 10, 38, 16, 18, 30, 16, 24, 12, 38, 2, 30, 17, 10, 38, 30, 16, 18, 29, 22, 41, 12, 30, 16, 0, 30, 16, 5, 10, 38, 5, 2, 12, 30, 16, 18, 38, 10, 38, 16, 31, 2, 10, 5, 2, 10, 38, 12, 12, 38, 33, 22, 10, 38, 2, 10, 38, 12, 12, 38, 16, 38, 16, 38, 18, -1, 26, 38, 10, 38, 16, 31, 16, 38, 12, 12, 38, 0, -1, 16, 30, 36, 6, -1, 31, 16, 16, 32, 27, 12, 22, 10, 38, 10, 22, 12, 38, 25, 38, 6, 6, 10, 38, 40, 12, 9, 36, 26, 2, 10, 38, 12, 12, 38, 12, 12, 22, 41, 12, 30, 18, 24, 2, 10, 38, 16, 30, 16, 0, 30, 17, 10, 21, 38, 12, 41, 5, 2, 10, 5, 32, 2, 10, 5, 2, 6, 10, 9, 26, 5, 10, 5, 2, 10, 27, 18, 6, 42, 38, 25, 22, 25, 22, 13, 22, 25, 22, 26, 38, 11, 22, 25, 22, 41, 2, 10, 5, 2, 10, 10, 30, 29, 38, 12, 30, 17, 10, 38, 12, 38, 25, 38, 16, 30, 2, 10, 22, 41, 18, 38, 5, 17, 10, 38, 42, 33, 30, 17, 10, 22, 12, 12, 38, 12, 12, 38, 10, 38, 16, 31, 30, 12, 12, 38, 12, 12, 38, 12, 12, 12, 38, 10, 38, 16, 30, 26, 16, 12, 38, 2, 10, 38, 11, 22, 11, 22, 11, 22, 10, 38, 26, 38, 33, 30, 17, 6, 10, 22, 12, 12, 38, 16, -1, 16, -1, 16, 31, 36, 18, 26, 38, 10, 38, 18, 38, 32, 31, 16, 5, 8, 38, 6, 0, 6, 22, 12, 12, 38, 25, 38, 25, 38, 6, 38, 41, 16, 30, 17, 10, 21, 5, 2, 10, 38, 25, 38, 25, 38, 16, 31, 6, 38, 10, 38, 12, 30, 17, 6, 10, 38, 2, 10, 38, 11, 22, 11, 22, 11, 22, 12, 38, 39, 6, 38, 26, 16, 10, 38, 16, 31, 24, 26, 2, 18, 6, 38, 12, 12, 38, 9, 36, 1, 16, 18, -1, 9, 16, 26, 24, 26, 17, 10, 38, 5, 16, 9, 38, 25, -1, 12, 41, 28, 21, 10, 42, 38, 18, 38, 33, 30, 2, 22, 12, 12, 38, 25, 38, 32, 30, 17, 10, 38, 12, 41, 5, 2, 10, 5, 16, 31, 42, 38, 16, 30, 5, 2, 10, 38, 41, 12, 5, 2, 10, 38, 12, 41, 28, 24, 2, 10, 42, 38, 18, 38, 33, 31, 16, 29, 5, 18, 22, 12, 12, 38, 25, -1, 25, -1, 2, 31, 17, 10, 11, 38, 12, 41, 28, 2, 6, 10, 42, 38, 33, 31, 18, 29, 5, 2, 1, 22, 12, 12, 41, 18, 42, 38, 25, 38, 11, 0, 10, 38, 12, 41, 5, 2, 10, 42, 38, 16, 30, 11, 0, 10, 5, 10, 38, 2, 10, 38, 6, 10, 10, 38, 11, 22, 6, 6, 10, 38, 11, 22, 6, 6, 10, 38, 11, 22, 12, 38, 25, 38, 0, 33, 30, 2, 22, 12, 12, 41, 18, 42, 38, 25, 38, 2, 10, 10, 38, 10, 38, 16, 30, 2, 10, 15, 10, 22, 16, 30, 2, 6, 10, 22, 16, 30, 2, 6, 10, 22, 41, 12, 11, 5, 2, 12, 38, 2, 10, 18, 5, 11, 15, 11, 38, 12, 12, 38, 25, 38, 2, 30, 6, 38, 2, 30, 6, 38, 2, 30, 6, 38, 41, 12, 30, 2, 10, 5, 17, 10, 38, 16, 30, 18, 24, 26, 38, 12, 12, 41, 18, 0, 18, 42, 38, 1, 10, 38, 1, 10, -1, 10, 38, 18, 38, 18, 5, 16, 38, 12, 12, 38, 5, 1, 11, 38, 6, 10, 38, 16, 31, 29, 16, 38, 28, 14, 17, 11, -1, 16, 31, -1, 16, 31, 16, 31, 36, 6, -1, 12, 38, 25, 38, 16, 31, 2, 10, 38, 12, 12, 38, 25, 38, 25, 38, 16, 31, 36, 6, 38, 16, 9, 36, 26, 38, 16, 31, 36, 18, 26, 38, 11, 31, 16, 7, 38, 16, 9, 26, 16, 22, 16, 31, 36, 18, 26, 16, 38, 11, 31, 6, 38, 16, 9, 26, 11, 38, 0, 16, 38, 25, 38, 25, 38, 25, 38, 16, 9, 36, 26, 38, 16, 9, 36, 26, 38, 25, 38, 26, 16, 38, 0, 16, 9, 36, 38, 41, 18, 12, 30, 29, 28, 1, 5, 17, 11, 38, 16, 30, 5, 2, 6, 10, 38, 30, 18, 18, 38, 0, 30, 17, 11, 18, 18, 5, 2, 10, 5, 2, 10, 15, 11, 38, 25, 38, 16, 31, 16, 26, 16, 38, 0, 38, 16, 9, 36, 26, 38, 12, 38, 25, 38, 32, 30, 18, 6, 38, 6, 10, 38, 2, 10, 38, 16, 31, 36, 28, 24, 26, 16, 38, 12, 12, 38, 0, 38, 18, 38, 18, 38, 16, 31, 36, 26, 38, 10, 38, 16, 31, 29, 24, 26, 38, 16, 31, 38, 41, 16, 30, 2, 10, 5, 10, 5, 17, 10, 38, 10, 38], 'genre': 'Drama', 'subgenre': 'drama', 'year': '1919', 'quarter_cent': '1900-1924', 'decade': '1910s', 'title': 'Fame and the poet', 'author': 'Dunsany [Edward John Moreton Drax Plunkett]', 'notes': '', 'comments': 'selected from larger file', 'period': '1850-1920', 'id': '317'} ``` ### Data Fields There are three configs in this dataset- `plain`, `class` and `pos`. `plain` is a simple text dataset whereas `pos` and `class` are both annotated datasets containing pos tagging. A `plain` data point has the following fields: ``` { "text": The text in the sample("string"), "genre": The genre of the text("string"), "subgenre": The subgenre of the text("string"), "year": The year the text was produced("string"), "quarter_cent": The quarter century in which the text was produced("string"), "decade": The decade the text was produced("string"), "title": The title of the text("string"), "author": The author of the text("string"), "notes": Notes about the text, if any("string"), "comments": Commentsabout the text, if any("string"), "period": 70-year period during which the text was produced("string"), "id": Unqiue identifier("string"), } ``` A typical `pos`/`class` data point has the following fields: ``` { "text": The tokens in the sample(list("string")), "pos_tags": Corresponding POS tags for the tokens (list("string")) "genre": The genre of the text("string"), "subgenre": The subgenre of the text("string"), "year": The year the text was produced("string"), "quarter_cent": The quarter century in which the text was produced("string"), "decade": The decade the text was produced("string"), "title": The title of the text("string"), "author": The author of the text("string"), "notes": Notes about the text, if any("string"), "comments": Commentsabout the text, if any("string"), "period": 70-year period during which the text was produced("string"), "id": Unqiue identifier("string"), } ``` ### Data Splits Train: 333 ## Dataset Creation ### Curation Rationale The Corpus of Late Modern English Texts (CLMET) is a corpus of roughly 35 million words of British English from 17101920, grouped into three 70-year periods (De Smet 2005; Diller et al. 2011). The history, versions and specifics of corpus composition can be followed up by referring to the CLMET3.0 website. CLMET3.0 is currently distributed in three formats: (i) plain text, (ii) plain text with one sentence per line, and (iii) a tagged version (one sentence per line). Version CLMET3.1 is the result of making CLMET available in a CQP format for use in CWB and CQPweb-based corpus environments (Evert & Hardie 2011; Evert 2010a). While there is no change to the selection of texts, CLMET3.1 includes additions and changes in linguistic annotation. The changes in CLMET3.1 are of three general types: (a) retokenization and retagging, (b) fixing of some systematic issues that come with historical data, and (c) enhancing annotation by adding lemmas and simplified part-of-speech class tags ### Source Data #### Initial Data Collection and Normalization The initial data is from OCR of texts in English from 1710-1920 #### Who are the source language producers? The text was produced by the authors of the original work and then OCRd ### Annotations #### Annotation process [Needs More Information] #### Who are the annotators? [Needs More Information] ### Personal and Sensitive Information This dataset does not contain any personal information as these are historic texts. Some content might be sensitive ## Considerations for Using the Data ### Social Impact of Dataset [Needs More Information] ### Discussion of Biases [Needs More Information] ### Other Known Limitations Dealing with historical data, tagging remains problematic in all areas, and should be treated with caution (especially with noun recognition) and/or combined with more coarse-grained class queries. Also bear in mind that the lemmas for unknown items are in lower case, while proper names that the tagger did recognize are not necessarily all lower case. In addition, lemmatization may not be consistent, e.g. in the area of -ize/ise spellings; these were not homogenized to preserve as much of the original orthography as possible. ## Additional Information ### Dataset Curators The Corpus of Late Modern English Texts, version 3.1 (CLMET3.1) has been created by Hendrik De Smet, Susanne Flach, Hans-J�rgen Diller and Jukka Tyrkk� ### Licensing Information Creative Commons Attribution Non Commercial Share Alike 4.0 International ### Citation Information [Needs More Information]
jordanparker6
null
null
null
false
1
false
jordanparker6/publaynet
2022-07-19T04:20:00.000Z
null
false
9baf6183ae9aeecfd261cb36f0d001e90bc77c57
[]
[ "arxiv:1908.07836", "title:PubLayNet", "license:other", "language:en", "size_categories:100B<n<1T", "task_categories:image-to-text" ]
https://huggingface.co/datasets/jordanparker6/publaynet/resolve/main/README.md
--- title: PubLayNet license: other annotations_creators: [] language: - en size_categories: - 100B<n<1T source_datasets: [] task_categories: - image-to-text task_ids: [] --- # PubLayNet PubLayNet is a large dataset of document images, of which the layout is annotated with both bounding boxes and polygonal segmentations. The source of the documents is [PubMed Central Open Access Subset (commercial use collection)](https://www.ncbi.nlm.nih.gov/pmc/tools/openftlist/). The annotations are automatically generated by matching the PDF format and the XML format of the articles in the PubMed Central Open Access Subset. More details are available in our paper ["PubLayNet: largest dataset ever for document layout analysis."](https://arxiv.org/abs/1908.07836). The public dataset is in tar.gz format which doesn't fit nicely with huggingface streaming. Modifications have been made to optimise the delivery of the dataset for the hugginface datset api. The original files can be found [here](https://developer.ibm.com/exchanges/data/all/publaynet/). Licence: [Community Data License Agreement – Permissive – Version 1.0 License](https://cdla.dev/permissive-1-0/) Author: IBM GitHub: https://github.com/ibm-aur-nlp/PubLayNet @article{ zhong2019publaynet, title = { PubLayNet: largest dataset ever for document layout analysis }, author = { Zhong, Xu and Tang, Jianbin and Yepes, Antonio Jimeno }, journal = { arXiv preprint arXiv:1908.07836}, year. = { 2019 } }
frgfm
null
@software{Howard_Imagenette_2019, title={Imagenette: A smaller subset of 10 easily classified classes from Imagenet}, author={Jeremy Howard}, year={2019}, month={March}, publisher = {GitHub}, url = {https://github.com/fastai/imagenette} }
Imagenette is a subset of 10 easily classified classes from Imagenet (tench, English springer, cassette player, chain saw, church, French horn, garbage truck, gas pump, golf ball, parachute).
false
2,946
false
frgfm/imagenette
2022-07-27T19:47:19.000Z
imagenette
false
4d512db4f6ee7d33feea15e2816facd8d292fef3
[]
[ "annotations_creators:crowdsourced", "language:en", "language_creators:crowdsourced", "license:apache-2.0", "size_categories:1K<n<10K", "source_datasets:extended", "task_categories:image-classification", "task_ids:image-classification" ]
https://huggingface.co/datasets/frgfm/imagenette/resolve/main/README.md
--- annotations_creators: - crowdsourced language: - en language_creators: - crowdsourced license: - apache-2.0 multilinguality: [] pretty_name: Imagenette size_categories: - 1K<n<10K source_datasets: - extended task_categories: - image-classification task_ids: - image-classification paperswithcode_id: imagenette --- # Dataset Card for Imagenette ## Table of Contents - [Table of Contents](#table-of-contents) - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - **Homepage:** https://github.com/fastai/imagenette - **Repository:** https://github.com/fastai/imagenette - **Leaderboard:** https://paperswithcode.com/sota/image-classification-on-imagenette ### Dataset Summary A smaller subset of 10 easily classified classes from [Imagenet](https://huggingface.co/datasets/imagenet-1k#dataset-summary), and a little more French. This dataset was created by [Jeremy Howard](https://twitter.com/jeremyphoward), and this repository is only there to share his work on this platform. The repository owner takes no credit of any kind in the creation, curation or packaging of the dataset. ### Supported Tasks and Leaderboards - `image-classification`: The dataset can be used to train a model for Image Classification. ### Languages The class labels in the dataset are in English. ## Dataset Structure ### Data Instances A data point comprises an image URL and its classification label. ``` { 'image': <PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=320x320 at 0x19FA12186D8>, 'label': 'tench', } ``` ### Data Fields - `image`: A `PIL.Image.Image` object containing the image. - `label`: the expected class label of the image. ### Data Splits | |train|validation| |----------|----:|---------:| |imagenette| 9469| 3925| ## Dataset Creation ### Curation Rationale cf. https://huggingface.co/datasets/imagenet-1k#curation-rationale ### Source Data #### Initial Data Collection and Normalization Imagenette is a subset of [ImageNet](https://huggingface.co/datasets/imagenet-1k). Information about data collection of the source data can be found [here](https://huggingface.co/datasets/imagenet-1k#initial-data-collection-and-normalization). ### Annotations #### Annotation process cf. https://huggingface.co/datasets/imagenet-1k#annotation-process #### Who are the annotators? cf. https://huggingface.co/datasets/imagenet-1k#who-are-the-annotators ### Personal and Sensitive Information cf. https://huggingface.co/datasets/imagenet-1k#personal-and-sensitive-information ## Considerations for Using the Data ### Social Impact of Dataset cf. https://huggingface.co/datasets/imagenet-1k#social-impact-of-dataset ### Discussion of Biases cf. https://huggingface.co/datasets/imagenet-1k#discussion-of-biases ### Other Known Limitations cf. https://huggingface.co/datasets/imagenet-1k#other-known-limitations ## Additional Information ### Dataset Curators cf. https://huggingface.co/datasets/imagenet-1k#dataset-curators and Jeremy Howard ### Licensing Information [Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0). ### Citation Information ``` @software{Howard_Imagenette_2019, title={Imagenette: A smaller subset of 10 easily classified classes from Imagenet}, author={Jeremy Howard}, year={2019}, month={March}, publisher = {GitHub}, url = {https://github.com/fastai/imagenette} } ``` ### Contributions This dataset was created by [Jeremy Howard](https://twitter.com/jeremyphoward) and published on [Github](https://github.com/fastai/imagenette). It was then only integrated into HuggingFace Datasets by [@frgfm](https://huggingface.co/frgfm).
SemiNeural
null
null
null
false
1
false
SemiNeural/MVdiffusion
2022-07-18T01:08:20.000Z
null
false
13b9a788d412e1e43f8e0446b1ee37211b360932
[]
[ "license:other" ]
https://huggingface.co/datasets/SemiNeural/MVdiffusion/resolve/main/README.md
--- license: other ---
tner
null
@inproceedings{derczynski-etal-2016-broad, title = "Broad {T}witter Corpus: A Diverse Named Entity Recognition Resource", author = "Derczynski, Leon and Bontcheva, Kalina and Roberts, Ian", booktitle = "Proceedings of {COLING} 2016, the 26th International Conference on Computational Linguistics: Technical Papers", month = dec, year = "2016", address = "Osaka, Japan", publisher = "The COLING 2016 Organizing Committee", url = "https://aclanthology.org/C16-1111", pages = "1169--1179", abstract = "One of the main obstacles, hampering method development and comparative evaluation of named entity recognition in social media, is the lack of a sizeable, diverse, high quality annotated corpus, analogous to the CoNLL{'}2003 news dataset. For instance, the biggest Ritter tweet corpus is only 45,000 tokens {--} a mere 15{\%} the size of CoNLL{'}2003. Another major shortcoming is the lack of temporal, geographic, and author diversity. This paper introduces the Broad Twitter Corpus (BTC), which is not only significantly bigger, but sampled across different regions, temporal periods, and types of Twitter users. The gold-standard named entity annotations are made by a combination of NLP experts and crowd workers, which enables us to harness crowd recall while maintaining high quality. We also measure the entity drift observed in our dataset (i.e. how entity representation varies over time), and compare to newswire. The corpus is released openly, including source text and intermediate annotations.", }
[BTC](https://aclanthology.org/C16-1111/)
false
185
false
tner/btc
2022-08-06T23:57:51.000Z
null
false
75179c320b8de3ca16c3494e8e1f8a397014ff1a
[]
[ "language:en", "license:other", "multilinguality:monolingual", "size_categories:1k<10K", "task_categories:token-classification", "task_ids:named-entity-recognition" ]
https://huggingface.co/datasets/tner/btc/resolve/main/README.md
--- language: - en license: - other multilinguality: - monolingual size_categories: - 1k<10K task_categories: - token-classification task_ids: - named-entity-recognition pretty_name: BTC --- # Dataset Card for "tner/btc" ## Dataset Description - **Repository:** [T-NER](https://github.com/asahi417/tner) - **Paper:** [https://aclanthology.org/C16-1111/](https://aclanthology.org/C16-1111/) - **Dataset:** Broad Twitter Corpus - **Domain:** Twitter - **Number of Entity:** 3 ### Dataset Summary Broad Twitter Corpus NER dataset formatted in a part of [TNER](https://github.com/asahi417/tner) project. - Entity Types: `LOC`, `ORG`, `PER` ## Dataset Structure ### Data Instances An example of `train` looks as follows. ``` { 'tokens': ['I', 'hate', 'the', 'words', 'chunder', ',', 'vomit', 'and', 'puke', '.', 'BUUH', '.'], 'tags': [6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6] } ``` ### Label ID The label2id dictionary can be found at [here](https://huggingface.co/datasets/tner/btc/raw/main/dataset/label.json). ```python { "B-LOC": 0, "B-ORG": 1, "B-PER": 2, "I-LOC": 3, "I-ORG": 4, "I-PER": 5, "O": 6 } ``` ### Data Splits | name |train|validation|test| |---------|----:|---------:|---:| |btc | 6338| 1001|2000| ### Citation Information ``` @inproceedings{derczynski-etal-2016-broad, title = "Broad {T}witter Corpus: A Diverse Named Entity Recognition Resource", author = "Derczynski, Leon and Bontcheva, Kalina and Roberts, Ian", booktitle = "Proceedings of {COLING} 2016, the 26th International Conference on Computational Linguistics: Technical Papers", month = dec, year = "2016", address = "Osaka, Japan", publisher = "The COLING 2016 Organizing Committee", url = "https://aclanthology.org/C16-1111", pages = "1169--1179", abstract = "One of the main obstacles, hampering method development and comparative evaluation of named entity recognition in social media, is the lack of a sizeable, diverse, high quality annotated corpus, analogous to the CoNLL{'}2003 news dataset. For instance, the biggest Ritter tweet corpus is only 45,000 tokens {--} a mere 15{\%} the size of CoNLL{'}2003. Another major shortcoming is the lack of temporal, geographic, and author diversity. This paper introduces the Broad Twitter Corpus (BTC), which is not only significantly bigger, but sampled across different regions, temporal periods, and types of Twitter users. The gold-standard named entity annotations are made by a combination of NLP experts and crowd workers, which enables us to harness crowd recall while maintaining high quality. We also measure the entity drift observed in our dataset (i.e. how entity representation varies over time), and compare to newswire. The corpus is released openly, including source text and intermediate annotations.", } ```
tner
null
@article{DBLP:journals/corr/abs-2201-07281, author = {Hang Jiang and Yining Hua and Doug Beeferman and Deb Roy}, title = {Annotating the Tweebank Corpus on Named Entity Recognition and Building {NLP} Models for Social Media Analysis}, journal = {CoRR}, volume = {abs/2201.07281}, year = {2022}, url = {https://arxiv.org/abs/2201.07281}, eprinttype = {arXiv}, eprint = {2201.07281}, timestamp = {Fri, 21 Jan 2022 13:57:15 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2201-07281.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
[Tweebank NER](https://arxiv.org/abs/2201.07281)
false
133
false
tner/tweebank_ner
2022-09-01T18:54:09.000Z
null
false
572a82169348679c5d92fe201cf3380463be540c
[]
[ "arxiv:2201.07281", "language:en", "license:other", "multilinguality:monolingual", "size_categories:1k<10K", "task_categories:token-classification", "task_ids:named-entity-recognition" ]
https://huggingface.co/datasets/tner/tweebank_ner/resolve/main/README.md
--- language: - en license: - other multilinguality: - monolingual size_categories: - 1k<10K task_categories: - token-classification task_ids: - named-entity-recognition pretty_name: TweeBank NER --- # Dataset Card for "tner/tweebank_ner" ## Dataset Description - **Repository:** [T-NER](https://github.com/asahi417/tner) - **Paper:** [https://arxiv.org/abs/2201.07281](https://arxiv.org/abs/2201.07281) - **Dataset:** TweeBank NER - **Domain:** Twitter - **Number of Entity:** 4 ### Dataset Summary TweeBank NER dataset formatted in a part of [TNER](https://github.com/asahi417/tner) project. - Entity Types: `LOC`, `MISC`, `PER`, `ORG` ## Dataset Structure ### Data Instances An example of `train` looks as follows. ``` { 'tokens': ['RT', '@USER2362', ':', 'Farmall', 'Heart', 'Of', 'The', 'Holidays', 'Tabletop', 'Christmas', 'Tree', 'With', 'Lights', 'And', 'Motion', 'URL1087', '#Holiday', '#Gifts'], 'tags': [8, 8, 8, 2, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8] } ``` ### Label ID The label2id dictionary can be found at [here](https://huggingface.co/datasets/tner/tweebank_ner/raw/main/dataset/label.json). ```python { "B-LOC": 0, "B-MISC": 1, "B-ORG": 2, "B-PER": 3, "I-LOC": 4, "I-MISC": 5, "I-ORG": 6, "I-PER": 7, "O": 8 } ``` ### Data Splits | name |train|validation|test| |---------|----:|---------:|---:| |tweebank_ner | 1639| 710 |1201| ### Citation Information ``` @article{DBLP:journals/corr/abs-2201-07281, author = {Hang Jiang and Yining Hua and Doug Beeferman and Deb Roy}, title = {Annotating the Tweebank Corpus on Named Entity Recognition and Building {NLP} Models for Social Media Analysis}, journal = {CoRR}, volume = {abs/2201.07281}, year = {2022}, url = {https://arxiv.org/abs/2201.07281}, eprinttype = {arXiv}, eprint = {2201.07281}, timestamp = {Fri, 21 Jan 2022 13:57:15 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2201-07281.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} } ```
tner
null
TBA
[TweetNER7](TBA)
false
241
false
tner/tweetner7
2022-10-11T02:55:38.000Z
null
false
5f0f25ab6ed3404063b316359fd0ca388e338ed4
[]
[ "arxiv:2210.03797", "language:en", "license:other", "multilinguality:monolingual", "size_categories:1k<10K", "task_categories:token-classification", "task_ids:named-entity-recognition" ]
https://huggingface.co/datasets/tner/tweetner7/resolve/main/README.md
--- language: - en license: - other multilinguality: - monolingual size_categories: - 1k<10K task_categories: - token-classification task_ids: - named-entity-recognition pretty_name: TweetNER7 --- # Dataset Card for "tner/tweetner7" ## Dataset Description - **Repository:** [https://github.com/asahi417/tner/tree/master/examples/tweetner7_paper](https://github.com/asahi417/tner/tree/master/examples/tweetner7_paper) - **Paper:** [https://arxiv.org/abs/2210.03797](https://arxiv.org/abs/2210.03797) - **Dataset:** TweetNER7 - **Domain:** Twitter - **Number of Entity:** 7 ### Dataset Summary This is the official repository of TweetNER7 (["Named Entity Recognition in Twitter: A Dataset and Analysis on Short-Term Temporal Shifts, AACL main conference 2022"](https://arxiv.org/abs/2210.03797)), an NER dataset on Twitter with 7 entity labels. Each instance of TweetNER7 comes with a timestamp which distributes from September 2019 to August 2021. The tweet collection used in TweetNER7 is same as what used in [TweetTopic](https://huggingface.co/datasets/cardiffnlp/tweet_topic_multi). The dataset is integrated in [TweetNLP](https://tweetnlp.org/) too. - Entity Types: `corperation`, `creative_work`, `event`, `group`, `location`, `product`, `person` ### Preprocessing We pre-process tweets before the annotation to normalize some artifacts, converting URLs into a special token `{{URL}}` and non-verified usernames into `{{USERNAME}}`. For verified usernames, we replace its display name (or account name) with symbols `{@}`. For example, a tweet ``` Get the all-analog Classic Vinyl Edition of "Takin' Off" Album from @herbiehancock via @bluenoterecords link below: http://bluenote.lnk.to/AlbumOfTheWeek ``` is transformed into the following text. ``` Get the all-analog Classic Vinyl Edition of "Takin' Off" Album from {@herbiehancock@} via {@bluenoterecords@} link below: {{URL}} ``` A simple function to format tweet follows below. ```python import re from urlextract import URLExtract extractor = URLExtract() def format_tweet(tweet): # mask web urls urls = extractor.find_urls(tweet) for url in urls: tweet = tweet.replace(url, "{{URL}}") # format twitter account tweet = re.sub(r"\b(\s*)(@[\S]+)\b", r'\1{\2@}', tweet) return tweet target = """Get the all-analog Classic Vinyl Edition of "Takin' Off" Album from @herbiehancock via @bluenoterecords link below: http://bluenote.lnk.to/AlbumOfTheWeek""" target_format = format_tweet(target) print(target_format) 'Get the all-analog Classic Vinyl Edition of "Takin\' Off" Album from {@herbiehancock@} via {@bluenoterecords@} link below: {{URL}}' ``` We ask annotators to ignore those special tokens but label the verified users' mentions. ### Data Split | split | number of instances | description | |:------------------|------:|------:| | train_2020 | 4616 | training dataset from September 2019 to August 2020 | | train_2021 | 2495 | training dataset from September 2020 to August 2021 | | train_all | 7111 | combined training dataset of `train_2020` and `train_2021` | | validation_2020 | 576 | validation dataset from September 2019 to August 2020 | | validation_2021 | 310 | validation dataset from September 2020 to August 2021 | | test_2020 | 576 | test dataset from September 2019 to August 2020 | | test_2021 | 2807 | test dataset from September 2020 to August 2021 | | train_random | 4616 | randomly sampled training dataset with the same size as `train_2020` from `train_all` | | validation_random | 576 | randomly sampled training dataset with the same size as `validation_2020` from `validation_all` | | extra_2020 | 87880 | extra tweet without annotations from September 2019 to August 2020 | | extra_2021 | 93594 | extra tweet without annotations from September 2020 to August 2021 | For the temporal-shift setting, model should be trained on `train_2020` with `validation_2020` and evaluate on `test_2021`. In general, model would be trained on `train_all`, the most representative training set with `validation_2021` and evaluate on `test_2021`. ## Dataset Structure ### Data Instances An example of `train` looks as follows. ``` { 'tokens': ['Morning', '5km', 'run', 'with', '{{USERNAME}}', 'for', 'breast', 'cancer', 'awareness', '#', 'pinkoctober', '#', 'breastcancerawareness', '#', 'zalorafit', '#', 'zalorafitxbnwrc', '@', 'The', 'Central', 'Park', ',', 'Desa', 'Parkcity', '{{URL}}'], 'tags': [14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 2, 14, 2, 14, 14, 14, 14, 14, 14, 4, 11, 11, 11, 11, 14], 'id': '1183344337016381440', 'date': '2019-10-13' } ``` ### Label ID The label2id dictionary can be found at [here](https://huggingface.co/datasets/tner/tweetner7/raw/main/dataset/label.json). ```python { "B-corporation": 0, "B-creative_work": 1, "B-event": 2, "B-group": 3, "B-location": 4, "B-person": 5, "B-product": 6, "I-corporation": 7, "I-creative_work": 8, "I-event": 9, "I-group": 10, "I-location": 11, "I-person": 12, "I-product": 13, "O": 14 } ``` ## Models See full evaluation metrics [here](https://github.com/asahi417/tner/blob/master/MODEL_CARD.md#models-for-tweetner7). ### Main Models | Model (link) | Data | Language Model | Micro F1 (2021) | Macro F1 (2021) | |:--------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------|------------------:|------------------:| | [`tner/roberta-large-tweetner7-all`](https://huggingface.co/tner/roberta-large-tweetner7-all) | [`tweetner7`](https://huggingface.co/datasets/tner/tweetner7) | [`roberta-large`](https://huggingface.co/roberta-large) | 65.75 | 61.25 | | [`tner/roberta-base-tweetner7-all`](https://huggingface.co/tner/roberta-base-tweetner7-all) | [`tweetner7`](https://huggingface.co/datasets/tner/tweetner7) | [`roberta-base`](https://huggingface.co/roberta-base) | 65.16 | 60.81 | | [`tner/twitter-roberta-base-2019-90m-tweetner7-all`](https://huggingface.co/tner/twitter-roberta-base-2019-90m-tweetner7-all) | [`tweetner7`](https://huggingface.co/datasets/tner/tweetner7) | [`cardiffnlp/twitter-roberta-base-2019-90m`](https://huggingface.co/cardiffnlp/twitter-roberta-base-2019-90m) | 65.68 | 61 | | [`tner/twitter-roberta-base-dec2020-tweetner7-all`](https://huggingface.co/tner/twitter-roberta-base-dec2020-tweetner7-all) | [`tweetner7`](https://huggingface.co/datasets/tner/tweetner7) | [`cardiffnlp/twitter-roberta-base-dec2020`](https://huggingface.co/cardiffnlp/twitter-roberta-base-dec2020) | 65.26 | 60.7 | | [`tner/bertweet-large-tweetner7-all`](https://huggingface.co/tner/bertweet-large-tweetner7-all) | [`tweetner7`](https://huggingface.co/datasets/tner/tweetner7) | [`cardiffnlp/twitter-roberta-base-dec2021vinai/bertweet-large`](https://huggingface.co/cardiffnlp/twitter-roberta-base-dec2021vinai/bertweet-large) | 66.46 | 61.87 | | [`tner/bertweet-base-tweetner7-all`](https://huggingface.co/tner/bertweet-base-tweetner7-all) | [`tweetner7`](https://huggingface.co/datasets/tner/tweetner7) | [`vinai/bertweet-base`](https://huggingface.co/vinai/bertweet-base) | 65.36 | 60.52 | | [`tner/bert-large-tweetner7-all`](https://huggingface.co/tner/bert-large-tweetner7-all) | [`tweetner7`](https://huggingface.co/datasets/tner/tweetner7) | [`bert-large`](https://huggingface.co/bert-large) | 63.58 | 59 | | [`tner/bert-base-tweetner7-all`](https://huggingface.co/tner/bert-base-tweetner7-all) | [`tweetner7`](https://huggingface.co/datasets/tner/tweetner7) | [`bert-base`](https://huggingface.co/bert-base) | 62.3 | 57.59 | | [`tner/roberta-large-tweetner7-continuous`](https://huggingface.co/tner/roberta-large-tweetner7-continuous) | [`tweetner7`](https://huggingface.co/datasets/tner/tweetner7) | [`roberta-large`](https://huggingface.co/roberta-large) | 66.02 | 60.9 | | [`tner/roberta-base-tweetner7-continuous`](https://huggingface.co/tner/roberta-base-tweetner7-continuous) | [`tweetner7`](https://huggingface.co/datasets/tner/tweetner7) | [`roberta-base`](https://huggingface.co/roberta-base) | 65.47 | 60.01 | | [`tner/twitter-roberta-base-2019-90m-tweetner7-continuous`](https://huggingface.co/tner/twitter-roberta-base-2019-90m-tweetner7-continuous) | [`tweetner7`](https://huggingface.co/datasets/tner/tweetner7) | [`cardiffnlp/twitter-roberta-base-2019-90m`](https://huggingface.co/cardiffnlp/twitter-roberta-base-2019-90m) | 65.87 | 61.07 | | [`tner/twitter-roberta-base-dec2020-tweetner7-continuous`](https://huggingface.co/tner/twitter-roberta-base-dec2020-tweetner7-continuous) | [`tweetner7`](https://huggingface.co/datasets/tner/tweetner7) | [`cardiffnlp/twitter-roberta-base-dec2020`](https://huggingface.co/cardiffnlp/twitter-roberta-base-dec2020) | 65.51 | 60.57 | | [`tner/bertweet-large-tweetner7-continuous`](https://huggingface.co/tner/bertweet-large-tweetner7-continuous) | [`tweetner7`](https://huggingface.co/datasets/tner/tweetner7) | [`cardiffnlp/twitter-roberta-base-dec2021vinai/bertweet-large`](https://huggingface.co/cardiffnlp/twitter-roberta-base-dec2021vinai/bertweet-large) | 66.41 | 61.66 | | [`tner/bertweet-base-tweetner7-continuous`](https://huggingface.co/tner/bertweet-base-tweetner7-continuous) | [`tweetner7`](https://huggingface.co/datasets/tner/tweetner7) | [`vinai/bertweet-base`](https://huggingface.co/vinai/bertweet-base) | 65.84 | 61.02 | | [`tner/bert-large-tweetner7-continuous`](https://huggingface.co/tner/bert-large-tweetner7-continuous) | [`tweetner7`](https://huggingface.co/datasets/tner/tweetner7) | [`bert-large`](https://huggingface.co/bert-large) | 63.2 | 57.67 | | [`tner/roberta-large-tweetner7-2021`](https://huggingface.co/tner/roberta-large-tweetner7-2021) | [`tweetner7`](https://huggingface.co/datasets/tner/tweetner7) | [`roberta-large`](https://huggingface.co/roberta-large) | 64.05 | 59.11 | | [`tner/roberta-base-tweetner7-2021`](https://huggingface.co/tner/roberta-base-tweetner7-2021) | [`tweetner7`](https://huggingface.co/datasets/tner/tweetner7) | [`roberta-base`](https://huggingface.co/roberta-base) | 61.76 | 57 | | [`tner/twitter-roberta-base-dec2020-tweetner7-2021`](https://huggingface.co/tner/twitter-roberta-base-dec2020-tweetner7-2021) | [`tweetner7`](https://huggingface.co/datasets/tner/tweetner7) | [`cardiffnlp/twitter-roberta-base-dec2020`](https://huggingface.co/cardiffnlp/twitter-roberta-base-dec2020) | 63.98 | 58.91 | | [`tner/bertweet-large-tweetner7-2021`](https://huggingface.co/tner/bertweet-large-tweetner7-2021) | [`tweetner7`](https://huggingface.co/datasets/tner/tweetner7) | [`cardiffnlp/twitter-roberta-base-dec2021vinai/bertweet-large`](https://huggingface.co/cardiffnlp/twitter-roberta-base-dec2021vinai/bertweet-large) | 62.9 | 58.13 | | [`tner/bertweet-base-tweetner7-2021`](https://huggingface.co/tner/bertweet-base-tweetner7-2021) | [`tweetner7`](https://huggingface.co/datasets/tner/tweetner7) | [`vinai/bertweet-base`](https://huggingface.co/vinai/bertweet-base) | 63.09 | 57.35 | | [`tner/bert-large-tweetner7-2021`](https://huggingface.co/tner/bert-large-tweetner7-2021) | [`tweetner7`](https://huggingface.co/datasets/tner/tweetner7) | [`bert-large`](https://huggingface.co/bert-large) | 59.75 | 53.93 | | [`tner/bert-base-tweetner7-2021`](https://huggingface.co/tner/bert-base-tweetner7-2021) | [`tweetner7`](https://huggingface.co/datasets/tner/tweetner7) | [`bert-base`](https://huggingface.co/bert-base) | 60.67 | 55.5 | | [`tner/roberta-large-tweetner7-2020`](https://huggingface.co/tner/roberta-large-tweetner7-2020) | [`tweetner7`](https://huggingface.co/datasets/tner/tweetner7) | [`roberta-large`](https://huggingface.co/roberta-large) | 64.76 | 60 | | [`tner/roberta-base-tweetner7-2020`](https://huggingface.co/tner/roberta-base-tweetner7-2020) | [`tweetner7`](https://huggingface.co/datasets/tner/tweetner7) | [`roberta-base`](https://huggingface.co/roberta-base) | 64.21 | 59.11 | | [`tner/twitter-roberta-base-2019-90m-tweetner7-2020`](https://huggingface.co/tner/twitter-roberta-base-2019-90m-tweetner7-2020) | [`tweetner7`](https://huggingface.co/datasets/tner/tweetner7) | [`cardiffnlp/twitter-roberta-base-2019-90m`](https://huggingface.co/cardiffnlp/twitter-roberta-base-2019-90m) | 64.28 | 59.31 | | [`tner/twitter-roberta-base-dec2020-tweetner7-2020`](https://huggingface.co/tner/twitter-roberta-base-dec2020-tweetner7-2020) | [`tweetner7`](https://huggingface.co/datasets/tner/tweetner7) | [`cardiffnlp/twitter-roberta-base-dec2020`](https://huggingface.co/cardiffnlp/twitter-roberta-base-dec2020) | 62.87 | 58.26 | | [`tner/bertweet-large-tweetner7-2020`](https://huggingface.co/tner/bertweet-large-tweetner7-2020) | [`tweetner7`](https://huggingface.co/datasets/tner/tweetner7) | [`cardiffnlp/twitter-roberta-base-dec2021vinai/bertweet-large`](https://huggingface.co/cardiffnlp/twitter-roberta-base-dec2021vinai/bertweet-large) | 64.01 | 59.47 | | [`tner/bertweet-base-tweetner7-2020`](https://huggingface.co/tner/bertweet-base-tweetner7-2020) | [`tweetner7`](https://huggingface.co/datasets/tner/tweetner7) | [`vinai/bertweet-base`](https://huggingface.co/vinai/bertweet-base) | 64.06 | 59.44 | | [`tner/bert-large-tweetner7-2020`](https://huggingface.co/tner/bert-large-tweetner7-2020) | [`tweetner7`](https://huggingface.co/datasets/tner/tweetner7) | [`bert-large`](https://huggingface.co/bert-large) | 61.43 | 56.14 | | [`tner/bert-base-tweetner7-2020`](https://huggingface.co/tner/bert-base-tweetner7-2020) | [`tweetner7`](https://huggingface.co/datasets/tner/tweetner7) | [`bert-base`](https://huggingface.co/bert-base) | 60.09 | 54.67 | Model description follows below. * Model with suffix `-all`: Model fine-tuned on `train_all` and validated on `validation_2021`. * Model with suffix `-continuous`: Model fine-tuned on `train_2021` continuously after fine-tuning on `train_2020` and validated on `validation_2021`. * Model with suffix `-2021`: Model fine-tuned only on `train_2021` and validated on `validation_2021`. * Model with suffix `-2020`: Model fine-tuned only on `train_2021` and validated on `validation_2020`. ### Sub Models (used in ablation study) - Model fine-tuned only on `train_random` and validated on `validation_2020`. | Model (link) | Data | Language Model | Micro F1 (2021) | Macro F1 (2021) | |:------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------|------------------:|------------------:| | [`tner/roberta-large-tweetner7-random`](https://huggingface.co/tner/roberta-large-tweetner7-random) | [`tweetner7`](https://huggingface.co/datasets/tner/tweetner7) | [`roberta-large`](https://huggingface.co/roberta-large) | 66.33 | 60.96 | | [`tner/twitter-roberta-base-2019-90m-tweetner7-random`](https://huggingface.co/tner/twitter-roberta-base-2019-90m-tweetner7-random) | [`tweetner7`](https://huggingface.co/datasets/tner/tweetner7) | [`cardiffnlp/twitter-roberta-base-2019-90m`](https://huggingface.co/cardiffnlp/twitter-roberta-base-2019-90m) | 63.29 | 58.5 | | [`tner/roberta-base-tweetner7-random`](https://huggingface.co/tner/roberta-base-tweetner7-random) | [`tweetner7`](https://huggingface.co/datasets/tner/tweetner7) | [`roberta-base`](https://huggingface.co/roberta-base) | 64.04 | 59.23 | | [`tner/twitter-roberta-base-dec2020-tweetner7-random`](https://huggingface.co/tner/twitter-roberta-base-dec2020-tweetner7-random) | [`tweetner7`](https://huggingface.co/datasets/tner/tweetner7) | [`cardiffnlp/twitter-roberta-base-dec2020`](https://huggingface.co/cardiffnlp/twitter-roberta-base-dec2020) | 64.72 | 59.97 | | [`tner/bertweet-large-tweetner7-random`](https://huggingface.co/tner/bertweet-large-tweetner7-random) | [`tweetner7`](https://huggingface.co/datasets/tner/tweetner7) | [`cardiffnlp/twitter-roberta-base-dec2021vinai/bertweet-large`](https://huggingface.co/cardiffnlp/twitter-roberta-base-dec2021vinai/bertweet-large) | 64.86 | 60.49 | | [`tner/bertweet-base-tweetner7-random`](https://huggingface.co/tner/bertweet-base-tweetner7-random) | [`tweetner7`](https://huggingface.co/datasets/tner/tweetner7) | [`vinai/bertweet-base`](https://huggingface.co/vinai/bertweet-base) | 65.55 | 59.58 | | [`tner/bert-large-tweetner7-random`](https://huggingface.co/tner/bert-large-tweetner7-random) | [`tweetner7`](https://huggingface.co/datasets/tner/tweetner7) | [`bert-large`](https://huggingface.co/bert-large) | 62.39 | 57.54 | | [`tner/bert-base-tweetner7-random`](https://huggingface.co/tner/bert-base-tweetner7-random) | [`tweetner7`](https://huggingface.co/datasets/tner/tweetner7) | [`bert-base`](https://huggingface.co/bert-base) | 60.91 | 55.92 | - Model fine-tuned on the self-labeled dataset on `extra_{2020,2021}` and validated on `validation_2020`. | Model (link) | Data | Language Model | Micro F1 (2021) | Macro F1 (2021) | |:----------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------|:--------------------------------------------------------|------------------:|------------------:| | [`tner/roberta-large-tweetner7-selflabel2020`](https://huggingface.co/tner/roberta-large-tweetner7-selflabel2020) | [`tweetner7`](https://huggingface.co/datasets/tner/tweetner7) | [`roberta-large`](https://huggingface.co/roberta-large) | 64.56 | 59.63 | | [`tner/roberta-large-tweetner7-selflabel2021`](https://huggingface.co/tner/roberta-large-tweetner7-selflabel2021) | [`tweetner7`](https://huggingface.co/datasets/tner/tweetner7) | [`roberta-large`](https://huggingface.co/roberta-large) | 64.6 | 59.45 | | [`tner/roberta-large-tweetner7-2020-selflabel2020-all`](https://huggingface.co/tner/roberta-large-tweetner7-2020-selflabel2020-all) | [`tweetner7`](https://huggingface.co/datasets/tner/tweetner7) | [`roberta-large`](https://huggingface.co/roberta-large) | 65.46 | 60.39 | | [`tner/roberta-large-tweetner7-2020-selflabel2021-all`](https://huggingface.co/tner/roberta-large-tweetner7-2020-selflabel2021-all) | [`tweetner7`](https://huggingface.co/datasets/tner/tweetner7) | [`roberta-large`](https://huggingface.co/roberta-large) | 64.52 | 59.45 | | [`tner/roberta-large-tweetner7-selflabel2020-continuous`](https://huggingface.co/tner/roberta-large-tweetner7-selflabel2020-continuous) | [`tweetner7`](https://huggingface.co/datasets/tner/tweetner7) | [`roberta-large`](https://huggingface.co/roberta-large) | 65.15 | 60.23 | | [`tner/roberta-large-tweetner7-selflabel2021-continuous`](https://huggingface.co/tner/roberta-large-tweetner7-selflabel2021-continuous) | [`tweetner7`](https://huggingface.co/datasets/tner/tweetner7) | [`roberta-large`](https://huggingface.co/roberta-large) | 64.48 | 59.41 | Model description follows below. * Model with suffix `-self2020`: Fine-tuning on the self-annotated data of `extra_2020` split of [tweetner7](https://huggingface.co/datasets/tner/tweetner7). * Model with suffix `-self2021`: Fine-tuning on the self-annotated data of `extra_2021` split of [tweetner7](https://huggingface.co/datasets/tner/tweetner7). * Model with suffix `-2020-self2020-all`: Fine-tuning on the self-annotated data of `extra_2020` split of [tweetner7](https://huggingface.co/datasets/tner/tweetner7). Combined training dataset of `extra_2020` and `train_2020`. * Model with suffix `-2020-self2021-all`: Fine-tuning on the self-annotated data of `extra_2021` split of [tweetner7](https://huggingface.co/datasets/tner/tweetner7). Combined training dataset of `extra_2021` and `train_2020`. * Model with suffix `-2020-self2020-continuous`: Fine-tuning on the self-annotated data of `extra_2020` split of [tweetner7](https://huggingface.co/datasets/tner/tweetner7). Fine-tuning on `train_2020` and continuing fine-tuning on `extra_2020`. * Model with suffix `-2020-self2021-continuous`: Fine-tuning on the self-annotated data of `extra_2021` split of [tweetner7](https://huggingface.co/datasets/tner/tweetner7). Fine-tuning on `train_2020` and continuing fine-tuning on `extra_2020`. ### Reproduce Experimental Result To reproduce the experimental result on our AACL paper, please see the repository [https://github.com/asahi417/tner/tree/master/examples/tweetner7_paper](https://github.com/asahi417/tner/tree/master/examples/tweetner7_paper). ## Citation Information ``` @inproceedings{ushio-etal-2022-tweet, title = "{N}amed {E}ntity {R}ecognition in {T}witter: {A} {D}ataset and {A}nalysis on {S}hort-{T}erm {T}emporal {S}hifts", author = "Ushio, Asahi and Neves, Leonardo and Silva, Vitor and Barbieri, Francesco. and Camacho-Collados, Jose", booktitle = "The 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing", month = nov, year = "2022", address = "Online", publisher = "Association for Computational Linguistics", } ```
bdura
null
null
null
false
3
false
bdura/swann
2022-07-18T10:55:59.000Z
null
false
2a9cbafadf550f3671a5d70fd13edfbe3924f50e
[]
[ "license:mit" ]
https://huggingface.co/datasets/bdura/swann/resolve/main/README.md
--- license: mit ---
fshllaku
null
null
null
false
3
false
fshllaku/test
2022-07-18T13:03:39.000Z
null
false
5d617042fffaa7876c93750add2a0a47b6f6826a
[]
[ "license:apache-2.0" ]
https://huggingface.co/datasets/fshllaku/test/resolve/main/README.md
--- license: apache-2.0 ---
Doohae
null
null
null
false
1
false
Doohae/marcopolo-v2-passage
2022-07-18T15:33:08.000Z
null
false
5bc51fd7d10388377950fee5a9612482d279e189
[]
[]
https://huggingface.co/datasets/Doohae/marcopolo-v2-passage/resolve/main/README.md
Top 20 hits for queries from training data in "MS-MARCO v2 passage" by Lucene Searcher (using pyserini) hits@20 0.1957 See also : https://github.com/castorini/pyserini/blob/master/docs/prebuilt-indexes.md For java11 installation in linux : https://stackoverflow.com/questions/52504825/how-to-install-jdk-11-under-ubuntu
neongeckocom
null
null
null
false
5
false
neongeckocom/cv-tts-clean
2022-09-29T20:44:12.000Z
null
false
d066df8bb6b8f2a837fa8bf8ff0fe1048e4a7b2f
[]
[ "license:bsd-3-clause" ]
https://huggingface.co/datasets/neongeckocom/cv-tts-clean/resolve/main/README.md
--- license: bsd-3-clause ---
allenai
null
@inproceedings{DeYoung2021MS2MS, title = {MSˆ2: Multi-Document Summarization of Medical Studies}, author = {Jay DeYoung and Iz Beltagy and Madeleine van Zuylen and Bailey Kuehl and Lucy Lu Wang}, booktitle = {EMNLP}, year = {2021} } @article{Wallace2020GeneratingN, title = {Generating (Factual?) Narrative Summaries of RCTs: Experiments with Neural Multi-Document Summarization}, author = {Byron C. Wallace and Sayantani Saha and Frank Soboczenski and Iain James Marshall}, year = 2020, journal = {AMIA Annual Symposium}, volume = {abs/2008.11293} }
The Multidocument Summarization for Literature Review (MSLR) Shared Task aims to study how medical evidence from different clinical studies are summarized in literature reviews. Reviews provide the highest quality of evidence for clinical care, but are expensive to produce manually. (Semi-)automation via NLP may facilitate faster evidence synthesis without sacrificing rigor. The MSLR shared task uses two datasets to assess the current state of multidocument summarization for this task, and to encourage the development of modeling contributions, scaffolding tasks, methods for model interpretability, and improved automated evaluation methods in this domain.
false
643
false
allenai/mslr2022
2022-07-18T16:54:34.000Z
multi-document-summarization
false
8c44d8bd2f493bd3b695f3a8bb44a53f6ba07763
[]
[ "annotations_creators:expert-generated", "language_creators:expert-generated", "language:en", "license:apache-2.0", "multilinguality:monolingual", "size_categories:10K<n<100K", "source_datasets:extended|other-MS^2", "source_datasets:extended|other-Cochrane", "task_categories:summarization", "task_...
https://huggingface.co/datasets/allenai/mslr2022/resolve/main/README.md
--- annotations_creators: - expert-generated language_creators: - expert-generated language: - en license: - apache-2.0 multilinguality: - monolingual size_categories: - 10K<n<100K source_datasets: - extended|other-MS^2 - extended|other-Cochrane task_categories: - summarization - text2text-generation task_ids: - summarization-other-query-based-summarization - summarization-other-query-based-multi-document-summarization - summarization-other-scientific-documents-summarization paperswithcode_id: multi-document-summarization pretty_name: MSLR Shared Task --- # Dataset Card for MSLR2022 ## Table of Contents - [Dataset Card for MSLR2022](#dataset-card-for-mslr2022) - [Table of Contents](#table-of-contents) - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Initial Data Collection and Normalization](#initial-data-collection-and-normalization) - [Who are the source language producers?](#who-are-the-source-language-producers) - [Annotations](#annotations) - [Annotation process](#annotation-process) - [Who are the annotators?](#who-are-the-annotators) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) ## Dataset Description - **Homepage:** https://github.com/allenai/mslr-shared-task - **Repository:** https://github.com/allenai/mslr-shared-task - **Paper:** https://aclanthology.org/2021.emnlp-main.594 - **Leaderboard:** https://github.com/allenai/mslr-shared-task#leaderboard - **Point of Contact:** https://github.com/allenai/mslr-shared-task#contact-us ### Dataset Summary The Multidocument Summarization for Literature Review (MSLR) Shared Task aims to study how medical evidence from different clinical studies are summarized in literature reviews. Reviews provide the highest quality of evidence for clinical care, but are expensive to produce manually. (Semi-)automation via NLP may facilitate faster evidence synthesis without sacrificing rigor. The MSLR shared task uses two datasets to assess the current state of multidocument summarization for this task, and to encourage the development of modeling contributions, scaffolding tasks, methods for model interpretability, and improved automated evaluation methods in this domain. ### Supported Tasks and Leaderboards This dataset is used for the MSLR2022 Shared Task. For information on the shared task leaderboard, please refer [here](https://github.com/allenai/mslr-shared-task#leaderboard). ### Languages English ## Dataset Structure More information on dataset structure [here](https://github.com/allenai/mslr-shared-task#data-structure). ### Data Instances __MS^2__ ```json { "review_id": "30760312", "pmid": [ "22776744", "25271670", "3493740", "1863023", "16291984", "23984728", "23996433", "18466198", "12151469", "27400308", "16053970", "22922316", "11897647", "11597664", "4230647" ], "title": [ "Improved Cell Survival and Paracrine Capacity of Human Embryonic Stem Cell-Derived Mesenchymal Stem Cells Promote Therapeutic Potential for Pulmonary Arterial Hypertension", "Adipose-derived stem cells attenuate pulmonary arterial hypertension and ameliorate pulmonary arterial remodeling in monocrotaline-induced pulmonary hypertensive rats", "Effect of bone marrow mesenchymal stem cells on experimental pulmonary arterial hypertension", "Survival in patients with primary pulmonary hypertension. Results from a national prospective registry.", "Sildenafil citrate therapy for pulmonary arterial hypertension.", "Macitentan and morbidity and mortality in pulmonary arterial hypertension.", "Long-term research of stem cells in monocrotaline-induced pulmonary arterial hypertension", "Safety and efficacy of autologous endothelial progenitor cells transplantation in children with idiopathic pulmonary arterial hypertension: open-label pilot study.", "Inhaled iloprost for severe pulmonary hypertension.", "Sildenafil reduces pulmonary vascular resistance in single ventricular physiology.", "Ambrisentan therapy for pulmonary arterial hypertension.", "Mesenchymal stem cell prevention of vascular remodeling in high flow-induced pulmonary hypertension through a paracrine mechanism.", "Continuous subcutaneous infusion of treprostinil, a prostacyclin analogue, in patients with pulmonary arterial hypertension: a double-blind, randomized, placebo-controlled trial.", "Effects of the dual endothelin-receptor antagonist bosentan in patients with pulmonary hypertension: a randomised placebocontrolled study", "SYRCLE\\u2019s risk of bias tool for animal studies" ], "abstract": [ "Although transplantation of adult bone marrow mesenchymal stem cells ( BM-MSCs ) holds promise in the treatment for pulmonary arterial hypertension ( PAH ) , the poor survival and differentiation potential of adult BM-MSCs have limited their therapeutic efficiency . Here , we compared the therapeutic efficacy of human embryonic stem cell-derived MSCs ( hESC-MSCs ) with adult BM-MSCs for the treatment of PAH in an animal model . One week following monocrotaline (MCT)-induced PAH , mice were r and omly assigned to receive phosphate-buffered saline ( MCT group ) ; 3.0 \\u00d7 106 human BM-derived MSCs ( BM-MSCs group ) or 3.0 \\u00d7 106 hESC-derived MSCs ( hESC-MSCs group ) via tail vein injection . At 3 weeks posttransplantation , the right ventricular systolic pressure ( RVSP ) , degree of RV hypertrophy , and medial wall thickening of pulmonary arteries were lower= , and pulmonary capillary density was higher in the hESC-MSC group as compared with BM-MSC and MCT groups ( all p < 0.05 ) . At 1 week posttransplantation , the number of engrafted MSCs in the lungs was found significantly higher in the hESC-MSC group than in the BM-MSC group ( all p < 0.01 ) . At 3 weeks posttransplantation , implanted BM-MSCs were undetectable whereas hESC-MSCs were not only engrafted in injured pulmonary arteries but had also undergone endothelial differentiation . In addition , protein profiling of hESC-MSC- and BM-MSC-conditioned medium revealed a differential paracrine capacity . Classification of these factors into bioprocesses revealed that secreted factors from hESC-MSCs were preferentially involved in early embryonic development and tissue differentiation , especially blood vessel morphogenesis . We concluded that improved cell survival and paracrine capacity of hESC-MSCs provide better therapeutic efficacy than BM-MSCs in the treatment for PAH", "Abstract We investigated the effect of adipose-derived stem cells ( ADSCs ) transplantation effects on structural remodeling and pulmonary artery pressure in monocrotaline (MCT)-induced pulmonary hypertensive rats . In the first experiment , 32 male Sprague-Dawley ( SD ) rats were r and omly divided into four groups ( n = 8/group ) : 3 ADSCs treated groups and normal control ( Ctrl ) . ADSCs were administered through the left jugular vein at 105 , 106 and 107 cells , respectively , and a cell density of 106cells/ml was shown to be optimal . The GFP-tagged ADSCs were identified in the lungs and differentiated into endothelial-like cells . In the second experiment , 96 male SD rats were r and omly divided into three groups ( n = 32/group ) : Ctrl , MCT-induced pulmonary arterial hypertension ( PAH ) , and PAH treated with ADSCs ( ADSCs ) . Two weeks post-MCT administration , the ADSCs group received 1 \\u00d7 106 ADSCs via the external jugular vein . Compared to PAH rats , mean pulmonary arterial pressure was decreased in rats at 1 , 2 , and 3 weeks after ADSCs-treatment ( 18.63 \\u00b1 2.15 mmHg versus 24.53 \\u00b1 2.90 mmHg ; 23.07 \\u00b1 2.84 mmHg versus 33.18 \\u00b1 2.30 mmHg ; 22.98 \\u00b1 2.34 mmHg versus 36.38 \\u00b1 3.28 mmHg , p < 0.05 ) . Meanwhile , the right heart hypertrophy index ( 36.2 1 \\u00b1 4.27 % versus 41.01 \\u00b1 1.29 % ; 39.47 \\u00b1 4.02 % versus 48.75 \\u00b1 2 .13 % ; 41.02 \\u00b1 0.9 % versus 50.52 \\u00b1 1.49 % , p < 0.05 , respectively ) , ratio of wall/lumen thickness , as well as the wall/lumen area were significantly reduced in PAH rats at these time points following ADSCs-treatment , as compared with untreated PAH rats . In summary , ADSCs may colonize the pulmonary arteries , attenuate pulmonary arterial hypertension and ameliorate pulmonary arterial remodeling", "The aim of the present study was to investigate the effect of bone marrow mesenchymal stem cell ( BMSC ) transp1antation on lung and heart damage in a rat model of monocrotaline (MCT)-induced pulmonary arterial hypertension ( PAH ) . The animals were r and omly divided into 3 groups : control , PAH and BMSC implantation groups . Structural changes in the pulmonary vascular wall , such as the pulmonary artery lumen area ( VA ) and vascular area ( TAA ) were measured by hematoxylin and eosin ( H&E ) staining , and the hemodynamics were detected by echocardiography . Two weeks post-operation , our results demonstrated that sublingual vein injection of BMSCs significantly attenuated the pulmonary vascular structural and hemodynamic changes caused by pulmonary arterial hypertension . The mechanism may be executed via paracrine effects", "OBJECTIVE To characterize mortality in persons diagnosed with primary pulmonary hypertension and to investigate factors associated with survival . DESIGN Registry with prospect i ve follow-up . SETTING Thirty-two clinical centers in the United States participating in the Patient Registry for the Characterization of Primary Pulmonary Hypertension supported by the National Heart , Lung , and Blood Institute . PATIENTS Patients ( 194 ) diagnosed at clinical centers between 1 July 1981 and 31 December 1985 and followed through 8 August 1988 . MEASUREMENTS At diagnosis , measurements of hemodynamic variables , pulmonary function , and gas exchange variables were taken in addition to information on demographic variables , medical history , and life-style . Patients were followed for survival at 6-month intervals . MAIN RESULTS The estimated median survival of these patients was 2.8 years ( 95 % Cl , 1.9 to 3.7 years ) . Estimated single-year survival rates were as follows : at 1 year , 68 % ( Cl , 61 % to 75 % ) ; at 3 years , 48 % ( Cl , 41 % to 55 % ) ; and at 5 years , 34 % ( Cl , 24 % to 44 % ) . Variables associated with poor survival included a New York Heart Association ( NYHA ) functional class of III or IV , presence of Raynaud phenomenon , elevated mean right atrial pressure , elevated mean pulmonary artery pressure , decreased cardiac index , and decreased diffusing capacity for carbon monoxide ( DLCO ) . Drug therapy at entry or discharge was not associated with survival duration . CONCLUSIONS Mortality was most closely associated with right ventricular hemodynamic function and can be characterized by means of an equation using three variables : mean pulmonary artery pressure , mean right atrial pressure , and cardiac index . Such an equation , once vali date d prospect ively , could be used as an adjunct in planning treatment strategies and allocating medical re sources", "BACKGROUND Sildenafil inhibits phosphodiesterase type 5 , an enzyme that metabolizes cyclic guanosine monophosphate , thereby enhancing the cyclic guanosine monophosphate-mediated relaxation and growth inhibition of vascular smooth-muscle cells , including those in the lung . METHODS In this double-blind , placebo-controlled study , we r and omly assigned 278 patients with symptomatic pulmonary arterial hypertension ( either idiopathic or associated with connective-tissue disease or with repaired congenital systemic-to-pulmonary shunts ) to placebo or sildenafil ( 20 , 40 , or 80 mg ) orally three times daily for 12 weeks . The primary end point was the change from baseline to week 12 in the distance walked in six minutes . The change in mean pulmonary-artery pressure and World Health Organization ( WHO ) functional class and the incidence of clinical worsening were also assessed , but the study was not powered to assess mortality . Patients completing the 12-week r and omized study could enter a long-term extension study . RESULTS The distance walked in six minutes increased from baseline in all sildenafil groups ; the mean placebo-corrected treatment effects were 45 m ( + 13.0 percent ) , 46 m ( + 13.3 percent ) , and 50 m ( + 14.7 percent ) for 20 , 40 , and 80 mg of sildenafil , respectively ( P<0.001 for all comparisons ) . All sildenafil doses reduced the mean pulmonary-artery pressure ( P=0.04 , P=0.01 , and P<0.001 , respectively ) , improved the WHO functional class ( P=0.003 , P<0.001 , and P<0.001 , respectively ) , and were associated with side effects such as flushing , dyspepsia , and diarrhea . The incidence of clinical worsening did not differ significantly between the patients treated with sildenafil and those treated with placebo . Among the 222 patients completing one year of treatment with sildenafil monotherapy , the improvement from baseline at one year in the distance walked in six minutes was 51 m. CONCLUSIONS Sildenafil improves exercise capacity , WHO functional class , and hemodynamics in patients with symptomatic pulmonary arterial hypertension", "BACKGROUND Current therapies for pulmonary arterial hypertension have been adopted on the basis of short-term trials with exercise capacity as the primary end point . We assessed the efficacy of macitentan , a new dual endothelin-receptor antagonist , using a primary end point of morbidity and mortality in a long-term trial . METHODS We r and omly assigned patients with symptomatic pulmonary arterial hypertension to receive placebo once daily , macitentan at a once-daily dose of 3 mg , or macitentan at a once-daily dose of 10 mg . Stable use of oral or inhaled therapy for pulmonary arterial hypertension , other than endothelin-receptor antagonists , was allowed at study entry . The primary end point was the time from the initiation of treatment to the first occurrence of a composite end point of death , atrial septostomy , lung transplantation , initiation of treatment with intravenous or subcutaneous prostanoids , or worsening of pulmonary arterial hypertension . RESULTS A total of 250 patients were r and omly assigned to placebo , 250 to the 3-mg macitentan dose , and 242 to the 10-mg macitentan dose . The primary end point occurred in 46.4 % , 38.0 % , and 31.4 % of the patients in these groups , respectively . The hazard ratio for the 3-mg macitentan dose as compared with placebo was 0.70 ( 97.5 % confidence interval [ CI ] , 0.52 to 0.96 ; P=0.01 ) , and the hazard ratio for the 10-mg macitentan dose as compared with placebo was 0.55 ( 97.5 % CI , 0.39 to 0.76 ; P<0.001 ) . Worsening of pulmonary arterial hypertension was the most frequent primary end-point event . The effect of macitentan on this end point was observed regardless of whether the patient was receiving therapy for pulmonary arterial hypertension at baseline . Adverse events more frequently associated with macitentan than with placebo were headache , nasopharyngitis , and anemia . CONCLUSIONS Macitentan significantly reduced morbidity and mortality among patients with pulmonary arterial hypertension in this event-driven study . ( Funded by Actelion Pharmaceuticals ; SERAPHIN Clinical Trials.gov number , NCT00660179 . )", "Our previous studies have shown that bone marrow mesenchymal stem cells ( BMSCs ) can inhibit the progression of pulmonary artery hypertension ( PAH ) in the monocrotaline ( MCT ) model in the short term . The aim of this study was to further investigate the long-term effect of BMSCs on PAH and to explore the mechanism of the protective effect including the pulmonary vascular remodeling and cell differentiation . PAH model was established by subcutaneous injection of 50 mg/kg MCT as previously study . Postoperatively , the animals were r and omly divided into three groups ( n = 10 in each group ) : control , PAH group , and BMSCs implantation group . Six months after injection , immunology and immunohistochemistry analysis indicated the MCT-induced intima-media thickness in muscular arteries was reduced ( P < 0.05 ) ; the area of collagen fibers in lung tissue was lower ( P < 0.05 ) , and the proliferating cell nuclear antigen level in pulmonary artery smooth muscle cells was decreased ( P < 0.05 ) . Immunofluorescence showed that the cells have the ability to differentiate between von Willebr and factor and vascular endothelial growth factor . Six months after intravenous injection , BMSCs could significantly improve pulmonary function by inhibiting the ventricular remodeling and the effect of cell differentiation", "Experimental data suggest that transplantation of EPCs attenuates monocrotaline-induced pulmonary hypertension in rats and dogs . In addition , our previous studies suggested that autologous EPC transplantation was feasible , safe , and might have beneficial effects on exercise capacity and pulmonary hemodynamics in adults with IPAH . Thus , we hypothesized that transplantation of EPCs would improve exercise capacity and pulmonary hemodynamics in children with IPAH . Thirteen children with IPAH received intravenous infusion of autologous EPCs . The right-sided heart catheterization and 6-MWD test were performed at baseline and at the time of 12 wk after cell infusion . At the time of 12 wk , mPAP decreased by 6.4 mmHg from 70.3 + /- 19.0 to 63.9 + /- 19.3 mmHg ( p = 0.015 ) . PVR decreased by approximately 19 % from 1118 + /- 537 to 906 + /- 377 dyn s/cm(5 ) ( p = 0.047 ) . CO increased from 3.39 + /- 0.79 to 3.85 + /- 0.42 L/min ( p = 0.048 ) . The 6-MWD increased by 39 m from 359 + /- 82 to 399 + /- 74 m ( p = 0.012 ) . NYHA functional class also improved . There were no severe adverse events with cell infusion . The small pilot study suggested that intravenous infusion of autologous EPCs was feasible , safe , and associated with significant improvements in exercise capacity , NYHA functional class , and pulmonary hemodynamics in children with IPAH . Confirmation of these results in a r and omized controlled trial are essential", "BACKGROUND Uncontrolled studies suggested that aerosolized iloprost , a stable analogue of prostacyclin , causes selective pulmonary vasodilatation and improves hemodynamics and exercise capacity in patients with pulmonary hypertension . METHODS We compared repeated daily inhalations of 2.5 or 5.0 microg of iloprost ( six or nine times per day ; median inhaled dose , 30 microg per day ) with inhalation of placebo . A total of 203 patients with selected forms of severe pulmonary arterial hypertension and chronic thromboembolic pulmonary hypertension ( New York Heart Association [ NYHA ] functional class III or IV ) were included . The primary end point was met if , after week 12 , the NYHA class and distance walked in six minutes were improved by at least one class and at least 10 percent , respectively , in the absence of clinical deterioration according to predefined criteria and death . RESULTS The combined clinical end point was met by 16.8 percent of the patients receiving iloprost , as compared with 4.9 percent of the patients receiving placebo ( P=0.007 ) . There were increases in the distance walked in six minutes of 36.4 m in the iloprost group as a whole ( P=0.004 ) and of 58.8 m in the subgroup of patients with primary pulmonary hypertension . Overall , 4.0 percent of patients in the iloprost group ( including one who died ) and 13.7 percent of those in the placebo group ( including four who died ) did not complete the study ( P=0.024 ) ; the most common reason for withdrawal was clinical deterioration . As compared with base-line values , hemodynamic values were significantly improved at 12 weeks when measured after iloprost inhalation ( P<0.001 ) , were largely unchanged when measured before iloprost inhalation , and were significantly worse in the placebo group . Further significant beneficial effects of iloprost treatment included an improvement in the NYHA class ( P=0.03 ) , dyspnea ( P=0.015 ) , and quality of life ( P=0.026 ) . Syncope occurred with similar frequency in the two groups but was more frequently rated as serious in the iloprost group , although this adverse effect was not associated with clinical deterioration . CONCLUSIONS Inhaled iloprost is an effective therapy for patients with severe pulmonary hypertension", "BACKGROUND High pulmonary vascular resistance ( PVR ) may be a risk factor for early and late mortality in both Glen shunt and Fontan operation patients . Furthermore , PVR may increase long after the Fontan operation . Whether pulmonary vasodilators such as phosphodiesterase 5 inhibitors can decrease PVR in patients with single ventricular physiology remains undetermined . METHODS AND RESULTS This was a prospect i ve , multicenter study . Patients with single ventricular physiology who have a PVR index higher than 2.5 Wood units \\u00b7 \\u33a1 ( WU ) were enrolled . Cardiac catheterization was performed before and after administration of sildenafil in all patients . After the Fontan operation , a six minute walk test ( 6MWT ) was also performed . A total of 42 patients were enrolled . PVR was significantly decreased in each stage of single ventricular physiology after sildenafil administration : from 4.3\\u00b11.5WU to 2.1\\u00b10.6WU ( p<0.01 ) in patients before a Glenn shunt , from 3.2\\u00b10.5WU to 1.6\\u00b10.6WU ( p<0.001 ) in patients after a Glenn shunt , and from 3.9\\u00b11.7WU to 2.3\\u00b10.8WU ( p<0.001 ) in patients after Fontan . In patients after Fontan , the 6MWT increased from 416\\u00b174 m to 485\\u00b172 m ( p<0.01 ) , and NYHA functional class improved significantly ( p<0.05 ) after sildenafil administration . No major side effects were observed in any patients . CONCLUSIONS Sildenafil reduced PVR in patients with single ventricle physiology . Sildenafil increased exercise capacity and improved NYHA functional class in patients after a Fontan operation . This implies that pulmonary vasodilation is a potential therapeutic target in selected patients with elevated PVR with single ventricle physiology . Long-term clinical significance warrants further study", "OBJECTIVES The purpose of this study was to examine the efficacy and safety of four doses of ambrisentan , an oral endothelin type A receptor-selective antagonist , in patients with pulmonary arterial hypertension ( PAH ) . BACKGROUND Pulmonary arterial hypertension is a life-threatening and progressive disease with limited treatment options . Endothelin is a vasoconstrictor and smooth muscle cell mitogen that plays a critical role in the pathogenesis and progression of PAH . METHODS In this double-blind , dose-ranging study , 64 patients with idiopathic PAH or PAH associated with collagen vascular disease , anorexigen use , or human immunodeficiency virus infection were r and omized to receive 1 , 2.5 , 5 , or 10 mg of ambrisentan once daily for 12 weeks followed by 12 weeks of open-label ambrisentan . The primary end point was an improvement from baseline in 6-min walk distance ( 6MWD ) ; secondary end points included Borg dyspnea index , World Health Organization ( WHO ) functional class , a subject global assessment , and cardiopulmonary hemodynamics . RESULTS At 12 weeks , ambrisentan increased 6MWD ( + 36.1 m , p < 0.0001 ) with similar and statistically significant increases for each dose group ( range , + 33.9 to + 38.1 m ) . Improvements were also observed in Borg dyspnea index , WHO functional class , subject global assessment , mean pulmonary arterial pressure ( -5.2 mm Hg , p < 0.0001 ) , and cardiac index ( + 0.33 l/min/m2 , p < 0.0008 ) . Adverse events were mild and unrelated to dose , including the incidence of elevated serum aminotransferase concentrations > 3 times the upper limit of normal ( 3.1 % ) . CONCLUSIONS Ambrisentan appears to improve exercise capacity , symptoms , and hemodynamics in patients with PAH . The incidence and severity of liver enzyme abnormalities appear to be low", "UNLABELLED Pulmonary arterial hypertension ( PAH ) is characterized by functional and structural changes in the pulmonary vasculature , and despite the drug treatment that made significant progress , the prognosis of patients with advanced PH remains extremely poor . In the present study , we investigated the early effect of bone marrow mesenchymal stem cells ( BMSCs ) on experimental high blood flow-induced PAH model rats and discussed the mechanism . BMSCs were isolated , cultured from bone marrow of Sprague-Dawley ( SD ) rat . The animal model of PAH was created by surgical methods to produce a left-to-right shunt . Following the successful establishment of the PAH model , rats were r and omly assigned to three groups ( n=20 in each group ) : sham group ( control ) , PAH group , and BMSC group ( received a sublingual vein injection of 1 - 5 \\u00d7 10(6 ) BMSCs ) . Two weeks after the administration , BMSCs significantly reduced the vascular remodeling , improved the hemodynamic data , and deceased the right ventricle weight ratio to left ventricular plus septal weight ( RV/LV+S ) ( P<0.05 ) . Real-time reverse transcription-polymerase chain reaction ( RT-PCR ) and immunohistochemistry analysis results indicated that the inflammation factors such as interleukin-1\\u03b2 ( IL-1\\u03b2 ) , IL-6 , and tumor necrosis factor-\\u03b1 ( TNF-\\u03b1 ) were reduced ( P<0.05 ) ; the expression of matrix metallo proteinase-9 ( MMP-9 ) was lower ( P<0.05 ) ; vascular endothelial growth factor ( VEGF ) was higher in BMSC group than those in PAH group ( P<0.05 ) . CONCLUSION Sublingual vein injection of BMSCs for 2 weeks , significantly improved the lung and heart injury caused by left-to-right shunt-induced PAH ; decreased pulmonary vascular remodeling and inflammation ; and enhanced angiogenesis", "Pulmonary arterial hypertension is a life-threatening disease for which continuous intravenous prostacyclin has proven to be effective . However , this treatment requires a permanent central venous catheter with the associated risk of serious complications such as sepsis , thromboembolism , or syncope . Treprostinil , a stable prostacyclin analogue , can be administered by a continuous subcutaneous infusion , avoiding these risks . We conducted a 12-week , double-blind , placebo-controlled multicenter trial in 470 patients with pulmonary arterial hypertension , either primary or associated with connective tissue disease or congenital systemic-to-pulmonary shunts . Exercise capacity improved with treprostinil and was unchanged with placebo ; the between treatment group difference in median six-minute walking distance was 16 m ( p = 0.006 ) . Improvement in exercise capacity was greater in the sicker patients and was dose-related , but independent of disease etiology . Concomitantly , treprostinil significantly improved indices of dyspnea , signs and symptoms of pulmonary hypertension , and hemodynamics . The most common side effect attributed to treprostinil was infusion site pain ( 85 % ) leading to premature discontinuation from the study in 8 % of patients . Three patients in the treprostinil treatment group presented with an episode of gastrointestinal hemorrhage . We conclude that chronic subcutaneous infusion of treprostinil is an effective treatment with an acceptable safety profile in patients with pulmonary arterial hypertension", "BACKGROUND Endothelin 1 , a powerful endogenous vasoconstrictor and mitogen , might be a cause of pulmonary hypertension . We describe the efficacy and safety of bosentan , a dual endothelin-receptor antagonist that can be taken orally , in patients with severe pulmonary hypertension . METHODS In this double-blind , placebo-controlled study , 32 patients with pulmonary hypertension ( primary or associated with scleroderma ) were r and omly assigned to bosentan ( 62.5 mg taken twice daily for 4 weeks then 125 mg twice daily ) or placebo for a minimum of 12 weeks . The primary endpoint was change in exercise capacity . Secondary endpoints included changes in cardiopulmonary haemodynamics , Borg dyspnoea index , WHO functional class , and withdrawal due to clinical worsening . Analysis was by intention to treat . FINDINGS In patients given bosentan , the distance walked in 6 min improved by 70 m at 12 weeks compared with baseline , whereas it worsened by 6 m in those on placebo ( difference 76 m [ 95 % CI 12 - 139 ] , p=0.021 ) . The improvement was maintained for at least 20 weeks . The cardiac index was 1.0 L min(-1 ) m(-2 ) ( 95 % CI 0.6 - 1.4 , p<0.0001 ) greater in patients given bosentan than in those given placebo . Pulmonary vascular resistance decreased by 223 dyn s cm(-)(5 ) with bosentan , but increased by 191 dyn s cm(-5 ) with placebo ( difference -415 [ -608 to -221 ] , p=0.0002 ) . Patients given bosentan had a reduced Borg dyspnoea index and an improved WHO functional class . All three withdrawals from clinical worsening were in the placebo group ( p=0.033 ) . The number and nature of adverse events did not differ between the two groups . INTERPRETATION Bosentan increases exercise capacity and improves haemodynamics in patients with pulmonary hypertension , suggesting that endothelin has an important role in pulmonary hypertension", "Background Systematic Review s ( SRs ) of experimental animal studies are not yet common practice , but awareness of the merits of conducting such SRs is steadily increasing . As animal intervention studies differ from r and omized clinical trials ( RCT ) in many aspects , the methodology for SRs of clinical trials needs to be adapted and optimized for animal intervention studies . The Cochrane Collaboration developed a Risk of Bias ( RoB ) tool to establish consistency and avoid discrepancies in assessing the method ological quality of RCTs . A similar initiative is warranted in the field of animal experimentation . Methods We provide an RoB tool for animal intervention studies ( SYRCLE \\u2019s RoB tool ) . This tool is based on the Cochrane RoB tool and has been adjusted for aspects of bias that play a specific role in animal intervention studies . To enhance transparency and applicability , we formulated signalling questions to facilitate judgment . Results The result ing RoB tool for animal studies contains 10 entries . These entries are related to selection bias , performance bias , detection bias , attrition bias , reporting bias and other biases . Half these items are in agreement with the items in the Cochrane RoB tool . Most of the variations between the two tools are due to differences in design between RCTs and animal studies . Shortcomings in , or unfamiliarity with , specific aspects of experimental design of animal studies compared to clinical studies also play a role . Conclusions SYRCLE \\u2019s RoB tool is an adapted version of the Cochrane RoB tool . Widespread adoption and implementation of this tool will facilitate and improve critical appraisal of evidence from animal studies . This may subsequently enhance the efficiency of translating animal research into clinical practice and increase awareness of the necessity of improving the method ological quality of animal studies" ], "target": "Conclusions SC therapy is effective for PAH in pre clinical studies .\\nThese results may help to st and ardise pre clinical animal studies and provide a theoretical basis for clinical trial design in the future .", "background": "Background Despite significant progress in drug treatment , the prognosis of patients with advanced pulmonary arterial hypertension ( PAH ) remains extremely poor .\\nMany pre clinical studies have reported the efficacy of stem cell ( SC ) therapy for PAH ; however , this approach remains controversial .\\nThe aim of this systematic review and meta- analysis is to assess the potential efficacy of SC therapy for PAH .", "reviews_info": "Background Despite significant progress in drug treatment , the prognosis of patients with advanced pulmonary arterial hypertension ( PAH ) remains extremely poor .\\nMany pre clinical studies have reported the efficacy of stem cell ( SC ) therapy for PAH ; however , this approach remains controversial .\\nThe aim of this systematic review and meta- analysis is to assess the potential efficacy of SC therapy for PAH ." } ``` __Cochrane__ ```json { "review_id": "CD007697", "pmid": [ "16394043" ], "title": [ "Aggressive surgical effort and improved survival in advanced-stage ovarian cancer." ], "abstract": [ "Residual disease after initial surgery for ovarian cancer is the strongest prognostic factor for survival. However, the extent of surgical resection required to achieve optimal cytoreduction is controversial. Our goal was to estimate the effect of aggressive surgical resection on ovarian cancer patient survival.\\n A retrospective cohort study of consecutive patients with International Federation of Gynecology and Obstetrics stage IIIC ovarian cancer undergoing primary surgery was conducted between January 1, 1994, and December 31, 1998. The main outcome measures were residual disease after cytoreduction, frequency of radical surgical resection, and 5-year disease-specific survival.\\n The study comprised 194 patients, including 144 with carcinomatosis. The mean patient age and follow-up time were 64.4 and 3.5 years, respectively. After surgery, 131 (67.5%) of the 194 patients had less than 1 cm of residual disease (definition of optimal cytoreduction). Considering all patients, residual disease was the only independent predictor of survival; the need to perform radical procedures to achieve optimal cytoreduction was not associated with a decrease in survival. For the subgroup of patients with carcinomatosis, residual disease and the performance of radical surgical procedures were the only independent predictors. Disease-specific survival was markedly improved for patients with carcinomatosis operated on by surgeons who most frequently used radical procedures compared with those least likely to use radical procedures (44% versus 17%, P < .001).\\n Overall, residual disease was the only independent predictor of survival. Minimizing residual disease through aggressive surgical resection was beneficial, especially in patients with carcinomatosis.\\n II-2." ], "target": "We found only low quality evidence comparing ultra-radical and standard surgery in women with advanced ovarian cancer and carcinomatosis. The evidence suggested that ultra-radical surgery may result in better survival.\\u00a0 It was unclear whether there were any differences in progression-free survival, QoL and morbidity between the two groups. The cost-effectiveness of this intervention has not been investigated. We are, therefore, unable to reach definite conclusions about the relative benefits and adverse effects of the two types of surgery.\\nIn order to determine the role of ultra-radical surgery in the management of advanced stage ovarian cancer, a sufficiently powered randomised controlled trial comparing ultra-radical and standard surgery or well-designed non-randomised studies would be required." } ``` ### Data Fields __MS^2__ - `"review_id"`: The PubMed ID of the review. - `"pmid"`: The PubMed IDs of the included studies. - `"title"`: The titles of the included studies. - `"abstract"`: The abstracts of the included studies. - `"target"`: The conclusions, taken from the abstract of the review, that serve as the summarization target. - `"background"`: A description of the reviews objective. __Cochrane__ - `"review_id"`: The PubMed ID of the review. - `"pmid"`: The PubMed IDs of the included studies. - `"title"`: The titles of the included studies. - `"abstract"`: The abstracts of the included studies. - `"target"`: The conclusions, taken from the abstract of the review, that serve as the summarization target. ### Data Splits Each dataset is split into training, validation and test partitions __MS^2__ | train | validation | test | |------:|-----------:|-----:| | 14188 | 2021 | 1667 | __Cochrane__ | train | validation | test | |------:|-----------:|-----:| | 3752 | 470 | 470 | ## Dataset Creation Please refer to the following papers for details about dataset curation: [MSˆ2: A Dataset for Multi-Document Summarization of Medical Studies](https://aclanthology.org/2021.emnlp-main.594.pdf) [Generating (Factual?) Narrative Summaries of RCTs: Experiments with Neural Multi-Document Summarization](https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8378607/) ### Curation Rationale [Needs More Information] ### Source Data #### Initial Data Collection and Normalization [Needs More Information] #### Who are the source language producers? [Needs More Information] ### Annotations #### Annotation process [Needs More Information] #### Who are the annotators? [Needs More Information] ### Personal and Sensitive Information [Needs More Information] ## Considerations for Using the Data ### Social Impact of Dataset [Needs More Information] ### Discussion of Biases [Needs More Information] ### Other Known Limitations [Needs More Information] ## Additional Information ### Dataset Curators [Needs More Information] ### Licensing Information Licensing information can be found [here](https://github.com/allenai/mslr-shared-task/blob/main/LICENSE). ### Citation Information **DeYoung, Jay, Iz Beltagy, Madeleine van Zuylen, Bailey Kuehl and Lucy Lu Wang. "MS2: A Dataset for Multi-Document Summarization of Medical Studies." EMNLP (2021).** ```bibtex @inproceedings{DeYoung2021MS2MS, title={MSˆ2: Multi-Document Summarization of Medical Studies}, author={Jay DeYoung and Iz Beltagy and Madeleine van Zuylen and Bailey Kuehl and Lucy Lu Wang}, booktitle={EMNLP}, year={2021} } ``` **Byron C. Wallace, Sayantani Saha, Frank Soboczenski, and Iain James Marshall. (2020). "Generating (factual?) narrative summaries of RCTs: Experiments with neural multi-document summarization." AMIA Annual Symposium.** ```bibtex @article{Wallace2020GeneratingN, title={Generating (Factual?) Narrative Summaries of RCTs: Experiments with Neural Multi-Document Summarization}, author={Byron C. Wallace and Sayantani Saha and Frank Soboczenski and Iain James Marshall}, journal={AMIA Annual Symposium}, year={2020}, volume={abs/2008.11293} } ```
yaakov
null
null
null
false
1
false
yaakov/wikipedia-de-splits
2022-07-18T18:28:34.000Z
null
false
db53cfec44e55e89ad01a01e1e75e5619d7be909
[]
[ "annotations_creators:no-annotation", "language_creators:crowdsourced", "license:cc-by-sa-3.0", "license:gfdl", "task_categories:text-generation", "task_categories:fill-mask", "task_ids:language-modeling", "task_ids:masked-language-modeling", "source_datasets:wikipedia", "size_categories:n<1K", ...
https://huggingface.co/datasets/yaakov/wikipedia-de-splits/resolve/main/README.md
--- annotations_creators: - no-annotation language_creators: - crowdsourced pretty_name: wikipedia-de-splits paperswithcode_id: null license: - cc-by-sa-3.0 - gfdl task_categories: - text-generation - fill-mask task_ids: - language-modeling - masked-language-modeling source_datasets: - wikipedia size_categories: - n<1K - 1K<n<10K - 10K<n<100K - 100K<n<1M - 1M<n<10M language: - de configs: - "1" - "2" - "3" - "4" - "5" - "6" - "7" - "8" - "9" - "10" - "11" - "12" - "13" - "14" - "15" - "16" - "17" - "18" - "19" - "20" - "21" - "all" --- # Dataset Card for yaakov/wikipedia-de-splits ## Dataset Description The only goal of this dataset is to have random German Wikipedia articles at various dataset sizes: Small datasets for fast development and large datasets for statistically relevant measurements. For this purpose, I loaded the 2665357 articles in the `test` set of the pre-processed German Wikipedia dump from 2022-03-01, randomly permuted the articles and created splits of sizes `2**n`: `1, 2, 4, 8, ...`. The split names are strings. The split `'all'` contains all 2665357 available articles. ## Dataset creation This dataset has been created with the following script: !apt install git-lfs !pip install -q transformers datasets from huggingface_hub import notebook_login notebook_login() from datasets import load_dataset wikipedia_de = load_dataset("wikipedia", "20220301.de")['train'] shuffled = wikipedia_de.shuffle(seed=42) from datasets import DatasetDict res = DatasetDict() k, n = 0, 1 while n <= shuffled.num_rows: res[str(k)] = shuffled.select(range(n)) k += 1; n *= 2 res['all'] = shuffled res.push_to_hub('yaakov/wikipedia-de-splits')
relbert
null
@inproceedings{jurgens-etal-2012-semeval, title = "{S}em{E}val-2012 Task 2: Measuring Degrees of Relational Similarity", author = "Jurgens, David and Mohammad, Saif and Turney, Peter and Holyoak, Keith", booktitle = "*{SEM} 2012: The First Joint Conference on Lexical and Computational Semantics {--} Volume 1: Proceedings of the main conference and the shared task, and Volume 2: Proceedings of the Sixth International Workshop on Semantic Evaluation ({S}em{E}val 2012)", month = "7-8 " # jun, year = "2012", address = "Montr{\'e}al, Canada", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/S12-1047", pages = "356--364", }
[SemEVAL 2012 task 2: Relational Similarity](https://aclanthology.org/S12-1047/)
false
154
false
relbert/semeval2012_relational_similarity
2022-07-20T18:56:37.000Z
null
false
9bdb7aefc0244fafa68e2ea3543d5068335296e1
[]
[ "language:en", "license:other", "multilinguality:monolingual", "size_categories:1K<n<10K" ]
https://huggingface.co/datasets/relbert/semeval2012_relational_similarity/resolve/main/README.md
--- language: - en license: - other multilinguality: - monolingual size_categories: - 1K<n<10K pretty_name: SemEval2012 task 2 Relational Similarity --- # Dataset Card for "relbert/semeval2012_relational_similarity" ## Dataset Description - **Repository:** [RelBERT](https://github.com/asahi417/relbert) - **Paper:** [https://aclanthology.org/S12-1047/](https://aclanthology.org/S12-1047/) - **Dataset:** SemEval2012: Relational Similarity ### Dataset Summary Relational similarity dataset from [SemEval2012 task 2](https://aclanthology.org/S12-1047/), compiled to fine-tune [RelBERT](https://github.com/asahi417/relbert) model. The dataset contains a list of positive and negative word pair from 89 pre-defined relations. The relation types are constructed on top of following 10 parent relation types. ```shell { 1: "Class Inclusion", # Hypernym 2: "Part-Whole", # Meronym, Substance Meronym 3: "Similar", # Synonym, Co-hypornym 4: "Contrast", # Antonym 5: "Attribute", # Attribute, Event 6: "Non Attribute", 7: "Case Relation", 8: "Cause-Purpose", 9: "Space-Time", 10: "Representation" } ``` Each of the parent relation is further grouped into child relation types where the definition can be found [here](https://drive.google.com/file/d/0BzcZKTSeYL8VenY0QkVpZVpxYnc/view?resourcekey=0-ZP-UARfJj39PcLroibHPHw). ## Dataset Structure ### Data Instances An example of `train` looks as follows. ``` { 'relation_type': '8d', 'positives': [ [ "breathe", "live" ], [ "study", "learn" ], [ "speak", "communicate" ], ... ] 'negatives': [ [ "starving", "hungry" ], [ "clean", "bathe" ], [ "hungry", "starving" ], ... ] } ``` ### Data Splits | name |train|validation| |---------|----:|---------:| |semeval2012_relational_similarity| 89 | 89| ### Number of Positive/Negative Word-pairs in each Split | relation_type | positive (train) | negative (train) | positive (validation) | negative (validation) | |:----------------|-------------------:|-------------------:|------------------------:|------------------------:| | 1 | 50 | 740 | 63 | 826 | | 10 | 60 | 730 | 66 | 823 | | 10a | 10 | 799 | 14 | 894 | | 10b | 10 | 797 | 13 | 893 | | 10c | 10 | 800 | 11 | 898 | | 10d | 10 | 799 | 10 | 898 | | 10e | 10 | 795 | 8 | 896 | | 10f | 10 | 799 | 10 | 898 | | 1a | 10 | 797 | 14 | 892 | | 1b | 10 | 797 | 14 | 892 | | 1c | 10 | 800 | 11 | 898 | | 1d | 10 | 797 | 16 | 890 | | 1e | 10 | 794 | 8 | 895 | | 2 | 100 | 690 | 117 | 772 | | 2a | 10 | 799 | 15 | 893 | | 2b | 10 | 796 | 11 | 894 | | 2c | 10 | 798 | 13 | 894 | | 2d | 10 | 798 | 10 | 897 | | 2e | 10 | 799 | 11 | 897 | | 2f | 10 | 802 | 11 | 900 | | 2g | 10 | 796 | 16 | 889 | | 2h | 10 | 799 | 11 | 897 | | 2i | 10 | 800 | 9 | 900 | | 2j | 10 | 801 | 10 | 900 | | 3 | 80 | 710 | 80 | 809 | | 3a | 10 | 799 | 11 | 897 | | 3b | 10 | 802 | 11 | 900 | | 3c | 10 | 798 | 12 | 895 | | 3d | 10 | 798 | 14 | 893 | | 3e | 10 | 802 | 5 | 906 | | 3f | 10 | 803 | 11 | 901 | | 3g | 10 | 801 | 6 | 904 | | 3h | 10 | 801 | 10 | 900 | | 4 | 80 | 710 | 82 | 807 | | 4a | 10 | 802 | 11 | 900 | | 4b | 10 | 797 | 7 | 899 | | 4c | 10 | 800 | 12 | 897 | | 4d | 10 | 796 | 4 | 901 | | 4e | 10 | 802 | 12 | 899 | | 4f | 10 | 802 | 9 | 902 | | 4g | 10 | 798 | 15 | 892 | | 4h | 10 | 801 | 12 | 898 | | 5 | 90 | 700 | 105 | 784 | | 5a | 10 | 798 | 14 | 893 | | 5b | 10 | 801 | 8 | 902 | | 5c | 10 | 799 | 11 | 897 | | 5d | 10 | 797 | 15 | 891 | | 5e | 10 | 801 | 8 | 902 | | 5f | 10 | 801 | 11 | 899 | | 5g | 10 | 802 | 9 | 902 | | 5h | 10 | 800 | 15 | 894 | | 5i | 10 | 800 | 14 | 895 | | 6 | 80 | 710 | 99 | 790 | | 6a | 10 | 798 | 15 | 892 | | 6b | 10 | 801 | 11 | 899 | | 6c | 10 | 801 | 13 | 897 | | 6d | 10 | 804 | 10 | 903 | | 6e | 10 | 801 | 11 | 899 | | 6f | 10 | 799 | 12 | 896 | | 6g | 10 | 798 | 12 | 895 | | 6h | 10 | 799 | 15 | 893 | | 7 | 80 | 710 | 91 | 798 | | 7a | 10 | 800 | 14 | 895 | | 7b | 10 | 796 | 7 | 898 | | 7c | 10 | 797 | 11 | 895 | | 7d | 10 | 800 | 14 | 895 | | 7e | 10 | 797 | 10 | 896 | | 7f | 10 | 796 | 12 | 893 | | 7g | 10 | 794 | 9 | 894 | | 7h | 10 | 795 | 14 | 890 | | 8 | 80 | 710 | 90 | 799 | | 8a | 10 | 797 | 14 | 892 | | 8b | 10 | 801 | 7 | 903 | | 8c | 10 | 796 | 12 | 893 | | 8d | 10 | 796 | 13 | 892 | | 8e | 10 | 796 | 11 | 894 | | 8f | 10 | 797 | 12 | 894 | | 8g | 10 | 793 | 7 | 895 | | 8h | 10 | 798 | 14 | 893 | | 9 | 90 | 700 | 96 | 793 | | 9a | 10 | 795 | 14 | 890 | | 9b | 10 | 799 | 12 | 896 | | 9c | 10 | 790 | 7 | 892 | | 9d | 10 | 803 | 9 | 903 | | 9e | 10 | 804 | 8 | 905 | | 9f | 10 | 799 | 10 | 898 | | 9g | 10 | 796 | 14 | 891 | | 9h | 10 | 799 | 13 | 895 | | 9i | 10 | 799 | 9 | 899 | | SUM | 1580 | 70207 | 1778 | 78820 | ### Citation Information ``` @inproceedings{jurgens-etal-2012-semeval, title = "{S}em{E}val-2012 Task 2: Measuring Degrees of Relational Similarity", author = "Jurgens, David and Mohammad, Saif and Turney, Peter and Holyoak, Keith", booktitle = "*{SEM} 2012: The First Joint Conference on Lexical and Computational Semantics {--} Volume 1: Proceedings of the main conference and the shared task, and Volume 2: Proceedings of the Sixth International Workshop on Semantic Evaluation ({S}em{E}val 2012)", month = "7-8 " # jun, year = "2012", address = "Montr{\'e}al, Canada", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/S12-1047", pages = "356--364", } ```
relbert
null
@inproceedings{ushio-etal-2021-bert, title = "{BERT} is to {NLP} what {A}lex{N}et is to {CV}: Can Pre-Trained Language Models Identify Analogies?", author = "Ushio, Asahi and Espinosa Anke, Luis and Schockaert, Steven and Camacho-Collados, Jose", booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)", month = aug, year = "2021", address = "Online", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2021.acl-long.280", doi = "10.18653/v1/2021.acl-long.280", pages = "3609--3624", abstract = "Analogies play a central role in human commonsense reasoning. The ability to recognize analogies such as {``}eye is to seeing what ear is to hearing{''}, sometimes referred to as analogical proportions, shape how we structure knowledge and understand language. Surprisingly, however, the task of identifying such analogies has not yet received much attention in the language model era. In this paper, we analyze the capabilities of transformer-based language models on this unsupervised task, using benchmarks obtained from educational settings, as well as more commonly used datasets. We find that off-the-shelf language models can identify analogies to a certain extent, but struggle with abstract and complex relations, and results are highly sensitive to model architecture and hyperparameters. Overall the best results were obtained with GPT-2 and RoBERTa, while configurations using BERT were not able to outperform word embedding models. Our results raise important questions for future work about how, and to what extent, pre-trained language models capture knowledge about abstract semantic relations.", }
[Analogy Question](https://aclanthology.org/2021.acl-long.280/)
false
4,486
false
relbert/analogy_questions
2022-07-20T23:19:25.000Z
null
false
a50076769d1b6491b7a283454ab4dbfb574afd6f
[]
[ "language:en", "license:other", "multilinguality:monolingual", "size_categories:n<1K" ]
https://huggingface.co/datasets/relbert/analogy_questions/resolve/main/README.md
--- language: - en license: - other multilinguality: - monolingual size_categories: - n<1K pretty_name: Analogy Question --- # Dataset Card for "relbert/analogy_questions" ## Dataset Description - **Repository:** [RelBERT](https://github.com/asahi417/relbert) - **Paper:** [https://aclanthology.org/2021.acl-long.280/](https://aclanthology.org/2021.acl-long.280/) - **Dataset:** Analogy Questions ### Dataset Summary This dataset contains 5 different word analogy questions used in [Analogy Language Model](https://aclanthology.org/2021.acl-long.280/). | name | Size (valid/test) | Num of choice | Num of relation group | Original Reference | |---------|------------------:|--------------:|----------------------:|:--------------------------------------------------------------------------:| | `sat_full`| -/374 | 5 | 2 | [Turney (2005)](https://arxiv.org/pdf/cs/0508053.pdf) | | `sat` | 37/337 | 5 | 2 | [Turney (2005)](https://arxiv.org/pdf/cs/0508053.pdf) | | `u2` | 24/228 | 5,4,3 | 9 | [EnglishForEveryone](https://englishforeveryone.org/Topics/Analogies.html) | | `u4` | 48/432 | 5,4,3 | 5 | [EnglishForEveryone](https://englishforeveryone.org/Topics/Analogies.html) | | `google` | 50/500 | 4 | 2 | [Mikolov et al., (2013)](https://www.aclweb.org/anthology/N13-1090.pdf) | | `bats` | 199/1799 | 4 | 3 | [Gladkova et al., (2016)](https://www.aclweb.org/anthology/N18-2017.pdf) | ## Dataset Structure ### Data Instances An example of `test` looks as follows. ``` { "stem": ["raphael", "painter"], "answer": 2, "choice": [["andersen", "plato"], ["reading", "berkshire"], ["marx", "philosopher"], ["tolstoi", "edison"]] } ``` The `stem` is the query word pair, `choice` has word pair candidates, and `answer` indicates the index of correct candidate which starts from `0`. All data is lowercased except Google dataset. ### Citation Information ``` @inproceedings{ushio-etal-2021-bert-is, title ={{BERT} is to {NLP} what {A}lex{N}et is to {CV}: {C}an {P}re-{T}rained {L}anguage {M}odels {I}dentify {A}nalogies?}, author={Ushio, Asahi and Espinosa-Anke, Luis and Schockaert, Steven and Camacho-Collados, Jose}, booktitle={Proceedings of the {ACL}-{IJCNLP} 2021 Main Conference}, year={2021}, publisher={Association for Computational Linguistics} } ``` ### LICENSE The LICENSE of all the resources are under [CC-BY-NC-4.0](./LICENSE). Thus, they are freely available for academic purpose or individual research, but restricted for commercial use.
teymur
null
null
null
false
1
false
teymur/art_schools
2022-07-18T18:42:41.000Z
null
false
d20edb6795642707df6470800216cd5941ee48fc
[]
[]
https://huggingface.co/datasets/teymur/art_schools/resolve/main/README.md
Muennighoff
null
@article{austin2021program, title={Program Synthesis with Large Language Models}, author={Austin, Jacob and Odena, Augustus and Nye, Maxwell and Bosma, Maarten and Michalewski, Henryk and Dohan, David and Jiang, Ellen and Cai, Carrie and Terry, Michael and Le, Quoc and others}, journal={arXiv preprint arXiv:2108.07732}, year={2021} }
The MBPP (Mostly Basic Python Problems) dataset consists of around 1,000 crowd-sourced Python programming problems, designed to be solvable by entry level programmers, covering programming fundamentals, standard library functionality, and so on. Each problem consists of a task description, code solution and 3 automated test cases.
false
29
false
Muennighoff/mbpp
2022-10-20T19:43:58.000Z
null
false
d81b8291e5998f5726ab7f35a0a557e761532aac
[]
[ "arxiv:2108.07732", "annotations_creators:crowdsourced", "annotations_creators:expert-generated", "language_creators:crowdsourced", "language_creators:expert-generated", "language:en", "license:cc-by-4.0", "multilinguality:monolingual", "size_categories:n<1K", "source_datasets:original", "task_c...
https://huggingface.co/datasets/Muennighoff/mbpp/resolve/main/README.md
--- annotations_creators: - crowdsourced - expert-generated language_creators: - crowdsourced - expert-generated language: - en license: - cc-by-4.0 multilinguality: - monolingual size_categories: - n<1K source_datasets: - original task_categories: - text2text-generation task_ids: [] pretty_name: Mostly Basic Python Problems tags: - code-generation --- # Dataset Card for Mostly Basic Python Problems (mbpp) ## Table of Contents - [Dataset Card for Mostly Basic Python Problems (mbpp)](#dataset-card-for-mostly-basic-python-problems-(mbpp)) - [Table of Contents](#table-of-contents) - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Initial Data Collection and Normalization](#initial-data-collection-and-normalization) - [Who are the source language producers?](#who-are-the-source-language-producers) - [Annotations](#annotations) - [Annotation process](#annotation-process) - [Who are the annotators?](#who-are-the-annotators) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - **Repository:** https://github.com/google-research/google-research/tree/master/mbpp - **Paper:** [Program Synthesis with Large Language Models](https://arxiv.org/abs/2108.07732) ### Dataset Summary The benchmark consists of around 1,000 crowd-sourced Python programming problems, designed to be solvable by entry level programmers, covering programming fundamentals, standard library functionality, and so on. Each problem consists of a task description, code solution and 3 automated test cases. As described in the paper, a subset of the data has been hand-verified by us. Released [here](https://github.com/google-research/google-research/tree/master/mbpp) as part of [Program Synthesis with Large Language Models, Austin et. al., 2021](https://arxiv.org/abs/2108.07732). ### Supported Tasks and Leaderboards This dataset is used to evaluate code generations. ### Languages English - Python code ## Dataset Structure ```python dataset_full = load_dataset("mbpp") DatasetDict({ test: Dataset({ features: ['task_id', 'text', 'code', 'test_list', 'test_setup_code', 'challenge_test_list'], num_rows: 974 }) }) dataset_sanitized = load_dataset("mbpp", "sanitized") DatasetDict({ test: Dataset({ features: ['source_file', 'task_id', 'prompt', 'code', 'test_imports', 'test_list'], num_rows: 427 }) }) ``` ### Data Instances #### mbpp - full ``` { 'task_id': 1, 'text': 'Write a function to find the minimum cost path to reach (m, n) from (0, 0) for the given cost matrix cost[][] and a position (m, n) in cost[][].', 'code': 'R = 3\r\nC = 3\r\ndef min_cost(cost, m, n): \r\n\ttc = [[0 for x in range(C)] for x in range(R)] \r\n\ttc[0][0] = cost[0][0] \r\n\tfor i in range(1, m+1): \r\n\t\ttc[i][0] = tc[i-1][0] + cost[i][0] \r\n\tfor j in range(1, n+1): \r\n\t\ttc[0][j] = tc[0][j-1] + cost[0][j] \r\n\tfor i in range(1, m+1): \r\n\t\tfor j in range(1, n+1): \r\n\t\t\ttc[i][j] = min(tc[i-1][j-1], tc[i-1][j], tc[i][j-1]) + cost[i][j] \r\n\treturn tc[m][n]', 'test_list': [ 'assert min_cost([[1, 2, 3], [4, 8, 2], [1, 5, 3]], 2, 2) == 8', 'assert min_cost([[2, 3, 4], [5, 9, 3], [2, 6, 4]], 2, 2) == 12', 'assert min_cost([[3, 4, 5], [6, 10, 4], [3, 7, 5]], 2, 2) == 16'], 'test_setup_code': '', 'challenge_test_list': [] } ``` #### mbpp - sanitized ``` { 'source_file': 'Benchmark Questions Verification V2.ipynb', 'task_id': 2, 'prompt': 'Write a function to find the shared elements from the given two lists.', 'code': 'def similar_elements(test_tup1, test_tup2):\n res = tuple(set(test_tup1) & set(test_tup2))\n return (res) ', 'test_imports': [], 'test_list': [ 'assert set(similar_elements((3, 4, 5, 6),(5, 7, 4, 10))) == set((4, 5))', 'assert set(similar_elements((1, 2, 3, 4),(5, 4, 3, 7))) == set((3, 4))', 'assert set(similar_elements((11, 12, 14, 13),(17, 15, 14, 13))) == set((13, 14))' ] } ``` ### Data Fields - `source_file`: unknown - `text`/`prompt`: description of programming task - `code`: solution for programming task - `test_setup_code`/`test_imports`: necessary code imports to execute tests - `test_list`: list of tests to verify solution - `challenge_test_list`: list of more challenging test to further probe solution ### Data Splits There are two version of the dataset (full and sanitized) which only one split each (test). ## Dataset Creation See section 2.1 of original [paper](https://arxiv.org/abs/2108.07732). ### Curation Rationale In order to evaluate code generation functions a set of simple programming tasks as well as solutions is necessary which this dataset provides. ### Source Data #### Initial Data Collection and Normalization The dataset was manually created from scratch. #### Who are the source language producers? The dataset was created with an internal crowdsourcing effort at Google. ### Annotations #### Annotation process The full dataset was created first and a subset then underwent a second round to improve the task descriptions. #### Who are the annotators? The dataset was created with an internal crowdsourcing effort at Google. ### Personal and Sensitive Information None. ## Considerations for Using the Data Make sure you execute generated Python code in a safe environment when evauating against this dataset as generated code could be harmful. ### Social Impact of Dataset With this dataset code generating models can be better evaluated which leads to fewer issues introduced when using such models. ### Discussion of Biases ### Other Known Limitations Since the task descriptions might not be expressive enough to solve the task. The `sanitized` split aims at addressing this issue by having a second round of annotators improve the dataset. ## Additional Information ### Dataset Curators Google Research ### Licensing Information CC-BY-4.0 ### Citation Information ``` @article{austin2021program, title={Program Synthesis with Large Language Models}, author={Austin, Jacob and Odena, Augustus and Nye, Maxwell and Bosma, Maarten and Michalewski, Henryk and Dohan, David and Jiang, Ellen and Cai, Carrie and Terry, Michael and Le, Quoc and others}, journal={arXiv preprint arXiv:2108.07732}, year={2021} ``` ### Contributions Thanks to [@lvwerra](https://github.com/lvwerra) for adding this dataset.
RaphaelOlivier
null
@inproceedings{panayotov2015librispeech, title={Librispeech: an ASR corpus based on public domain audio books}, author={Panayotov, Vassil and Chen, Guoguo and Povey, Daniel and Khudanpur, Sanjeev}, booktitle={Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference on}, pages={5206--5210}, year={2015}, organization={IEEE} }
LibriSpeech is a corpus of approximately 1000 hours of read English speech with sampling rate of 16 kHz, prepared by Vassil Panayotov with the assistance of Daniel Povey. The data is derived from read audiobooks from the LibriVox project, and has been carefully segmented and aligned. Note that in order to limit the required storage for preparing this dataset, the audio is stored in the .flac format and is not converted to a float32 array. To convert, the audio file to a float32 array, please make use of the `.map()` function as follows: ```python import soundfile as sf def map_to_array(batch): speech_array, _ = sf.read(batch["file"]) batch["speech"] = speech_array return batch dataset = dataset.map(map_to_array, remove_columns=["file"]) ```
false
1
false
RaphaelOlivier/librispeech_asr_adversarial
2022-08-03T00:02:08.000Z
null
false
c692cd0d633f0a920eb45833ec64f748b9e7ca72
[]
[]
https://huggingface.co/datasets/RaphaelOlivier/librispeech_asr_adversarial/resolve/main/README.md
# Description This dataset is a subset of [https://huggingface.co/datasets/librispeech_asr](LibriSpeech) that has been adversarially modified. It is designed to fool ASR models into predicting a target of our choosing instead of the correct output. ## Splits The dataset contains several splits. Each split consists of the same utterances, modified with different types and amount of noise. 3 noises have been used: * Adversarial noise of radius 0.04 (`adv_0.04` split) * Adversarial noise of radius 0.015 (`adv_0.015` split) * Adversarial noise of radius 0.015 combined with Room Impulse Response (RIR) noise (`adv_0.015_RIR` split) In addition we provide the original inputs (`natural` split) For each split we actually provide two text keys: `true_text` which is the original LibriSpeech label, i.e. the sentence one can actually hear when listening to the audio; and `target_text`, which is the target sentence of our adversarial attack. An ASR model that this dataset fools would get a low WER on `target_text` and a high WER on `true_text`. An ASR model robust to this dataset would get the opposite. ## Usage You should evaluate your model on this dataset as you would evaluate it on LibriSpeech. Here is an example with Wav2Vec2 ```python from datasets import load_dataset from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor import torch from jiwer import wer librispeech_adv_eval = load_dataset("RaphaelOlivier/librispeech_asr_adversarial", "adv", split="adv_0.15_adv_txt") model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-base-960h").to("cuda") processor = Wav2Vec2Processor.from_pretrained("facebook/wav2vec2-base-960h") def map_to_pred(batch): input_values = processor(batch["audio"]["array"], return_tensors="pt", padding="longest").input_values with torch.no_grad(): logits = model(input_values.to("cuda")).logits predicted_ids = torch.argmax(logits, dim=-1) transcription = processor.batch_decode(predicted_ids) batch["transcription"] = transcription return batch result = librispeech_adv_eval.map(map_to_pred, batched=True, batch_size=1, remove_columns=["audio"]) print("WER on correct labels:", wer(result["true_text"], result["transcription"])) print("WER on attack targets:", wer(result["target_text"], result["transcription"])) ``` *Result (WER)*: | "0.015 target_text" | "0.015 true_text" | "0.04 target_text" | "0.04 true_text" |---|---|---|---| | 58.2 | 108 | 49.5 | 108 |
autoevaluate
null
null
null
false
1
false
autoevaluate/autoeval-staging-eval-project-rajistics__indian_food_images-7f4d71b4-11165495
2022-07-18T20:03:52.000Z
null
false
db08ee5f909bebfadfdee104a5653078574e8602
[]
[ "type:predictions", "tags:autotrain", "tags:evaluation", "datasets:rajistics/indian_food_images" ]
https://huggingface.co/datasets/autoevaluate/autoeval-staging-eval-project-rajistics__indian_food_images-7f4d71b4-11165495/resolve/main/README.md
--- type: predictions tags: - autotrain - evaluation datasets: - rajistics/indian_food_images eval_info: task: image_multi_class_classification model: rajistics/finetuned-indian-food metrics: [] dataset_name: rajistics/indian_food_images dataset_config: rajistics--indian_food_images dataset_split: test col_mapping: image: image target: label --- # Dataset Card for AutoTrain Evaluator This repository contains model predictions generated by [AutoTrain](https://huggingface.co/autotrain) for the following task and dataset: * Task: Multi-class Image Classification * Model: rajistics/finetuned-indian-food * Dataset: rajistics/indian_food_images * Config: rajistics--indian_food_images * Split: test To run new evaluation jobs, visit Hugging Face's [automatic model evaluator](https://huggingface.co/spaces/autoevaluate/model-evaluator). ## Contributions Thanks to [@@rajistics](https://huggingface.co/@rajistics) for evaluating this model.
autoevaluate
null
null
null
false
3
false
autoevaluate/autoeval-staging-eval-project-kmfoda__booksum-7d55fc88-11175496
2022-07-19T06:04:56.000Z
null
false
dac358f5f9e237b2670b04bf261c3c200326257d
[]
[ "type:predictions", "tags:autotrain", "tags:evaluation", "datasets:kmfoda/booksum" ]
https://huggingface.co/datasets/autoevaluate/autoeval-staging-eval-project-kmfoda__booksum-7d55fc88-11175496/resolve/main/README.md
--- type: predictions tags: - autotrain - evaluation datasets: - kmfoda/booksum eval_info: task: summarization model: pszemraj/long-t5-tglobal-base-16384-booksum-V11 metrics: [] dataset_name: kmfoda/booksum dataset_config: kmfoda--booksum dataset_split: test col_mapping: text: chapter target: summary_text --- # Dataset Card for AutoTrain Evaluator This repository contains model predictions generated by [AutoTrain](https://huggingface.co/autotrain) for the following task and dataset: * Task: Summarization * Model: pszemraj/long-t5-tglobal-base-16384-booksum-V11 * Dataset: kmfoda/booksum * Config: kmfoda--booksum * Split: test To run new evaluation jobs, visit Hugging Face's [automatic model evaluator](https://huggingface.co/spaces/autoevaluate/model-evaluator). ## Contributions Thanks to [@pszemraj](https://huggingface.co/pszemraj) for evaluating this model.
nateraw
null
null
null
false
1
false
nateraw/documentation-images
2022-11-15T23:01:19.000Z
null
false
0e98000dfa312ec05ca8e9ad9c0988ac0df5435a
[]
[ "license:mit" ]
https://huggingface.co/datasets/nateraw/documentation-images/resolve/main/README.md
--- license: mit ---
biglam
null
@misc{20.500.12024/3193, title = {The Lampeter Corpus of Early Modern English Tracts}, url = {http://hdl.handle.net/20.500.12024/3193}, note = {Oxford Text Archive}, copyright = {Distributed by the University of Oxford under a Creative Commons Attribution-{ShareAlike} 3.0 Unported License},
The Lampeter Corpus of Early Modern English Tracts is a collection of texts on various subject matter published between 1640 and 1740 – a time that is marked by the rise of mass publication, the development of a public discourse in many areas of everyday life and, last but not least, the standardisation of British English.
false
1
false
biglam/lampeter_corpus
2022-09-15T15:52:46.000Z
null
false
24b7cc19e0ca633cccf49ad39a42e8feca1ac4d1
[]
[ "annotations_creators:no-annotation", "language:en", "language_creators:found", "license:cc-by-sa-3.0", "multilinguality:monolingual", "size_categories:n<1K", "source_datasets:original", "task_categories:text-classification", "task_ids:multi-label-classification", "task_ids:multi-class-classificat...
https://huggingface.co/datasets/biglam/lampeter_corpus/resolve/main/README.md
--- annotations_creators: - no-annotation paperswithcode_id: null language: - en language_creators: - found license: - cc-by-sa-3.0 multilinguality: - monolingual pretty_name: Lampeter Corpus size_categories: - n<1K source_datasets: - original task_categories: - text-classification task_ids: - multi-label-classification - multi-class-classification --- # Dataset Card for lampeter_corpus ## Table of Contents - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-instances) - [Data Splits](#data-instances) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) ## Dataset Description - **Homepage:** https://ota.bodleian.ox.ac.uk/repository/xmlui/handle/20.500.12024/3193 - **Repository:** [Needs More Information] - **Paper:** [Needs More Information] - **Leaderboard:** [Needs More Information] - **Point of Contact:** Josef Schmied, Claudia Claridge, Rainer Siemund ### Dataset Summary The Lampeter Corpus of Early Modern English Tracts is a collection of texts on various subject matter published between 1640 and 1740,  a time that was marked by the rise of mass publication, the development of public discourse in many areas of everyday life and last but not least, the standardisation of British English. Each text belongs to one of the following genres: Law, Economy, Religion, Politics, Science, Miscellaneous ### Supported Tasks and Leaderboards - `text-classification`: This dataset comes with dates and genre classifications for each text which can be used to finetune a model for text classification. ### Languages The text in the dataset is British English. The associated BCP-47 code is `en-GB` ## Dataset Structure ### Data Instances A typical data point contains an id, a text, the head of the text (which can be missing on some occasions) and the title. The two features which can be used for classification are `date`, which is the year of publication and `genre` which classifies the text into one of six broad areas. ``` { 'id': 'SciB1735', 'text': '\nI. WHEN I read your Defence of the British Mathematicians, I could not, Sir, but admire your Courage in asserting with such undoubting Assurance things so easily disproved. This to me seemed unaccountable, till I reflected on what you say (p. 32.) when upon my having appealed to every thinking Reader, whether it be possible to frame any clear Conception of Fluxions, you express yourself in the following manner, "Pray, Sir, who are those thinking Readers you ap\npeal to? Are they Geometricians, or Persons wholly ignorant of Geometry? If the former, I leave it to them: If the latter, I ask how well are they qualified to judge of the Method of Fluxions"? It must be acknowledged you seem by this Dilemma secure in the favour of one Part of your Readers, and the ignorance of the other. I am nevertheless persuaded there are fair and candid Men among the Mathematicians. And for those who are not Mathematicians, I shall endeavour so to unveil this Mystery, [TRUNCATED]', 'date': '1735', 'genre': 'Science', ' head': 'A DEFENCE OF FREE-THINKING IN Mathematics; &c.\n', 'title': 'A defence of free-thinking in mathematics [...]' } ``` ### Data Fields The dataset contains the following fields: - `id`: Unique identifier("string"), - `text`: ext in the document("string"), - `date`: Date of publication("date64"), - `genre`: Broad classification("string"), - `head`: Often same as title. Can be missing("string"), - `title`: Title of document("string") ### Data Splits Train: 120 ## Dataset Creation ### Curation Rationale The period covered by the Lampeter Corpus, 1640 to 1740, marks a crucial period in English history and the elaboration of English as a multi-purpose language. The texts selected for the corpus reflect the standardisation process of English and historical developments between the outbreak of the Civil War and the beginning of the Industrial Revolution. To meet the needs of linguists and historians alike, the Lampeter project has attempted to create a balanced corpus rather than a randomly chosen archive or collection. A balanced corpus, then, is characterised by several transparent sampling criteria. ### Source Data #### Initial Data Collection and Normalization The original data is selected according to the following criteria: - Complete texts only, including dedications, prefaces, postscripts, etc. - Texts are of varying length, ranging from c. 3,000 to c. 20,000 words. - Each author appears only once to avoid idiosyncratic language use. - Major literary figures of the time were excluded since their writing style can be studied in other, existing collections. - Generally, only first editions of the texts; later editions only if changes were made by the original authors, thus ensuring the authenticity of the language. #### Who are the source language producers? Authors of texts between 1640-1740 ### Annotations #### Annotation process N/A #### Who are the annotators? N/A ### Personal and Sensitive Information N/A ## Considerations for Using the Data ### Social Impact of Dataset N/A ### Discussion of Biases The social biases of the time in terms of race, sex, gender, etc. might be encountered in this dataset ### Other Known Limitations None ## Additional Information ### Dataset Curators Josef Schmied, Claudia Claridge, Rainer Siemund ### Licensing Information Creative Commons Attribution-ShareAlike 3.0 Unported (CC BY-SA 3.0) ### Citation Information University of Oxford, The Lampeter Corpus of Early Modern English Tracts, Oxford Text Archive, http://hdl.handle.net/20.500.12024/3193.
breakend
null
@article{nllb2022, author = {NLLB Team, Marta R. Costa-jussà, James Cross, Onur Çelebi, Maha Elbayad, Kenneth Heafield, Kevin Heffernan, Elahe Kalbassi, Janice Lam, Daniel Licht, Jean Maillard, Anna Sun, Skyler Wang, Guillaume Wenzek, Al Youngblood, Bapi Akula, Loic Barrault, Gabriel Mejia Gonzalez, Prangthip Hansanti, John Hoffman, Semarley Jarrett, Kaushik Ram Sadagopan, Dirk Rowe, Shannon Spruit, Chau Tran, Pierre Andrews, Necip Fazil Ayan, Shruti Bhosale, Sergey Edunov, Angela Fan, Cynthia Gao, Vedanuj Goswami, Francisco Guzmán, Philipp Koehn, Alexandre Mourachko, Christophe Ropers, Safiyyah Saleem, Holger Schwenk, Jeff Wang}, title = {No Language Left Behind: Scaling Human-Centered Machine Translation}, year = {2022} }
NLLB Multi Domain is a set of professionally-translated sentences in News, Unscripted informal speech, and Health domains. It is designed to enable assessment of out-of-domain performance and to study domain adaptation for machine translation. Each domain has approximately 3000 sentences.
false
1
false
breakend/nllb-multi-domain
2022-08-09T20:44:23.000Z
flores
false
017c5c5cada61bfacf5431573b0d054d7a9ce6c6
[]
[ "arxiv:2207.04672", "language:en", "language:ru", "language:ayr", "language:bho", "language:dyu", "language:fur", "language:wol", "annotations_creators:found", "language_creators:expert-generated", "license:cc-by-sa-4.0", "multilinguality:multilingual", "multilinguality:translation", "size...
https://huggingface.co/datasets/breakend/nllb-multi-domain/resolve/main/README.md
--- language: - en - ru - ayr - bho - dyu - fur - wol annotations_creators: - found language_creators: - expert-generated license: - cc-by-sa-4.0 multilinguality: - multilingual - translation pretty_name: nllb-multi-domain size_categories: - unknown source_datasets: - extended|flores task_categories: - conditional-text-generation task_ids: - machine-translation paperswithcode_id: flores --- # Dataset Card for NLLB Multi-Domain ## Table of Contents - [Dataset Card for NLLB Multi-Domain](#dataset-card-for-nllb-multi-domain) - [Table of Contents](#table-of-contents) - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) ## Dataset Description - **Home:** [Flores](https://github.com/facebookresearch/flores/tree/main/nllb_md) - **Repository:** [Github](https://github.com/facebookresearch/flores/tree/main/nllb_md) ### Dataset Summary NLLB Multi Domain is a set of professionally-translated sentences in News, Unscripted informal speech, and Health domains. It is designed to enable assessment of out-of-domain performance and to study domain adaptation for machine translation. Each domain has approximately 3000 sentences. ### Supported Tasks and Leaderboards #### Multilingual Machine Translation Refer to the [Dynabench leaderboard](https://dynabench.org/flores/Flores%20MT%20Evaluation%20(FULL)) for additional details on model evaluation on FLORES-101 in the context of the WMT2021 shared task on [Large-Scale Multilingual Machine Translation](http://www.statmt.org/wmt21/large-scale-multilingual-translation-task.html). Flores 200 is an extention of this. ### Languages Language | FLORES-200 code ---|--- Central Aymara | ayr_Latn Bhojpuri | bho_Deva Dyula | dyu_Latn Friulian | fur_Latn Russian | rus_Cyrl Wolof | wol_Latn Use a hyphenated pairing to get two langauges in one datapoint (e.g., "eng_Latn-rus_Cyrl" will provide sentences in the format below). ## Dataset Structure ### Data Instances See Dataset Viewer. The text is provided as-in the original dataset, without further preprocessing or tokenization. ### Data Fields - `id`: Row number for the data entry, starting at 1. - `sentence`: The full sentence in the specific language (may have _lang for pairings) - `domain`: The domain of the sentence. ### Dataset Creation Please refer to the original article [No Language Left Behind: Scaling Human-Centered Machine Translation](https://arxiv.org/abs/2207.04672) for additional information on dataset creation. ## Additional Information ### Dataset Curators See paper for details. ### Licensing Information Licensed with Creative Commons Attribution Share Alike 4.0. License available [here](https://creativecommons.org/licenses/by-sa/4.0/). ### Citation Information Please cite the authors if you use these corpora in your work: ```bibtex @article{nllb2022, author = {NLLB Team, Marta R. Costa-jussà, James Cross, Onur Çelebi, Maha Elbayad, Kenneth Heafield, Kevin Heffernan, Elahe Kalbassi, Janice Lam, Daniel Licht, Jean Maillard, Anna Sun, Skyler Wang, Guillaume Wenzek, Al Youngblood, Bapi Akula, Loic Barrault, Gabriel Mejia Gonzalez, Prangthip Hansanti, John Hoffman, Semarley Jarrett, Kaushik Ram Sadagopan, Dirk Rowe, Shannon Spruit, Chau Tran, Pierre Andrews, Necip Fazil Ayan, Shruti Bhosale, Sergey Edunov, Angela Fan, Cynthia Gao, Vedanuj Goswami, Francisco Guzmán, Philipp Koehn, Alexandre Mourachko, Christophe Ropers, Safiyyah Saleem, Holger Schwenk, Jeff Wang}, title = {No Language Left Behind: Scaling Human-Centered Machine Translation}, year = {2022} } ``` Please also cite prior work that this dataset builds on: ```bibtex @inproceedings{, title={The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation}, author={Goyal, Naman and Gao, Cynthia and Chaudhary, Vishrav and Chen, Peng-Jen and Wenzek, Guillaume and Ju, Da and Krishnan, Sanjana and Ranzato, Marc'Aurelio and Guzm\'{a}n, Francisco and Fan, Angela}, year={2021} } ``` ```bibtex @inproceedings{, title={Two New Evaluation Datasets for Low-Resource Machine Translation: Nepali-English and Sinhala-English}, author={Guzm\'{a}n, Francisco and Chen, Peng-Jen and Ott, Myle and Pino, Juan and Lample, Guillaume and Koehn, Philipp and Chaudhary, Vishrav and Ranzato, Marc'Aurelio}, journal={arXiv preprint arXiv:1902.01382}, year={2019} } ```
autoevaluate
null
null
null
false
3
false
autoevaluate/autoeval-staging-eval-project-samsum-e4148a42-11205497
2022-07-19T00:46:59.000Z
null
false
7cf9edbb26f77e278980a0a7274c9b9cfe736a0a
[]
[ "type:predictions", "tags:autotrain", "tags:evaluation", "datasets:samsum" ]
https://huggingface.co/datasets/autoevaluate/autoeval-staging-eval-project-samsum-e4148a42-11205497/resolve/main/README.md
--- type: predictions tags: - autotrain - evaluation datasets: - samsum eval_info: task: summarization model: pszemraj/led-large-book-summary metrics: ['perplexity'] dataset_name: samsum dataset_config: samsum dataset_split: test col_mapping: text: dialogue target: summary --- # Dataset Card for AutoTrain Evaluator This repository contains model predictions generated by [AutoTrain](https://huggingface.co/autotrain) for the following task and dataset: * Task: Summarization * Model: pszemraj/led-large-book-summary * Dataset: samsum * Config: samsum * Split: test To run new evaluation jobs, visit Hugging Face's [automatic model evaluator](https://huggingface.co/spaces/autoevaluate/model-evaluator). ## Contributions Thanks to [@pszemraj](https://huggingface.co/pszemraj) for evaluating this model.
autoevaluate
null
null
null
false
1
false
autoevaluate/autoeval-staging-eval-project-samsum-e4148a42-11205498
2022-07-19T00:11:46.000Z
null
false
ad38a8b3a538f495d14beab585c71d704249645b
[]
[ "type:predictions", "tags:autotrain", "tags:evaluation", "datasets:samsum" ]
https://huggingface.co/datasets/autoevaluate/autoeval-staging-eval-project-samsum-e4148a42-11205498/resolve/main/README.md
--- type: predictions tags: - autotrain - evaluation datasets: - samsum eval_info: task: summarization model: pszemraj/long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP metrics: ['perplexity'] dataset_name: samsum dataset_config: samsum dataset_split: test col_mapping: text: dialogue target: summary --- # Dataset Card for AutoTrain Evaluator This repository contains model predictions generated by [AutoTrain](https://huggingface.co/autotrain) for the following task and dataset: * Task: Summarization * Model: pszemraj/long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP * Dataset: samsum * Config: samsum * Split: test To run new evaluation jobs, visit Hugging Face's [automatic model evaluator](https://huggingface.co/spaces/autoevaluate/model-evaluator). ## Contributions Thanks to [@pszemraj](https://huggingface.co/pszemraj) for evaluating this model.
gorkemozkaya
null
null
null
false
1
false
gorkemozkaya/blended_en_tr
2022-07-19T05:29:32.000Z
null
false
00d6311c524f0c3e5d420dce399855e3ee777cba
[]
[ "license:other" ]
https://huggingface.co/datasets/gorkemozkaya/blended_en_tr/resolve/main/README.md
--- license: other ---
gorkaartola
null
null
null
false
1
false
gorkaartola/ZS_on_SDG_Descriptions_S1-sentence_S2-SDGtitle_Negative_Sample_Filter-All
2022-09-06T14:45:08.000Z
null
false
7c2e7e455a7a832656bcc0fb0e299e2af85f9778
[]
[]
https://huggingface.co/datasets/gorkaartola/ZS_on_SDG_Descriptions_S1-sentence_S2-SDGtitle_Negative_Sample_Filter-All/resolve/main/README.md
label_ids: - (0) contradiction - (2) entailment
gorkaartola
null
null
null
false
1
false
gorkaartola/ZS_on_SDG_Descriptions_S1-sentence_S2-SDGtitle_Negative_Sample_Filter-None
2022-09-06T14:45:55.000Z
null
false
2f101624310c129a6303a1f4f3df70a191357911
[]
[]
https://huggingface.co/datasets/gorkaartola/ZS_on_SDG_Descriptions_S1-sentence_S2-SDGtitle_Negative_Sample_Filter-None/resolve/main/README.md
label_ids: - (0) contradiction - (2) entailment
gorkaartola
null
null
null
false
1
false
gorkaartola/ZS_on_SDG_Descriptions_S1-sentence_S2-SDGtitle_Negative_Sample_Filter-Only_Title
2022-09-06T14:48:25.000Z
null
false
7b02284135e8ef3867e5fc168f9bbb9cbd355335
[]
[]
https://huggingface.co/datasets/gorkaartola/ZS_on_SDG_Descriptions_S1-sentence_S2-SDGtitle_Negative_Sample_Filter-Only_Title/resolve/main/README.md
label_ids: - (0) contradiction - (2) entailment
PierreMeester
null
null
null
false
1
false
PierreMeester/TestBloom
2022-07-19T11:28:06.000Z
null
false
231d3567e46d83cc26158c2a712862e27a633dda
[]
[ "license:afl-3.0" ]
https://huggingface.co/datasets/PierreMeester/TestBloom/resolve/main/README.md
--- license: afl-3.0 ---
autoevaluate
null
null
null
false
2
false
autoevaluate/autoeval-staging-eval-project-f9efad07-2209-4d77-9230-9fd08f3882ea-41
2022-07-19T14:25:37.000Z
null
false
aa7465b952ba969304d1a6b8f32b7bbb00873fbb
[]
[ "type:predictions", "tags:autotrain", "tags:evaluation", "datasets:squad" ]
https://huggingface.co/datasets/autoevaluate/autoeval-staging-eval-project-f9efad07-2209-4d77-9230-9fd08f3882ea-41/resolve/main/README.md
--- type: predictions tags: - autotrain - evaluation datasets: - squad eval_info: task: extractive_question_answering model: autoevaluate/extractive-question-answering metrics: [] dataset_name: squad dataset_config: plain_text dataset_split: validation col_mapping: context: context question: question answers-text: answers.text answers-answer_start: answers.answer_start --- # Dataset Card for AutoTrain Evaluator This repository contains model predictions generated by [AutoTrain](https://huggingface.co/autotrain) for the following task and dataset: * Task: Question Answering * Model: autoevaluate/extractive-question-answering * Dataset: squad * Config: plain_text * Split: validation To run new evaluation jobs, visit Hugging Face's [automatic model evaluator](https://huggingface.co/spaces/autoevaluate/model-evaluator). ## Contributions Thanks to [@lewtun](https://huggingface.co/lewtun) for evaluating this model.
albertvillanova
null
null
null
false
1
false
albertvillanova/dummy_tags
2022-07-19T12:45:12.000Z
null
false
cde78f02852c8d40801626a4e54802f560797583
[]
[ "language:en", "tags:test", "tags:dummy" ]
https://huggingface.co/datasets/albertvillanova/dummy_tags/resolve/main/README.md
--- language: - en tags: - test - dummy --- # Dataset Card for dummy_tags
liyangbing
null
null
null
false
1
false
liyangbing/water
2022-07-19T13:11:13.000Z
null
false
f7f915d4676a984516b6dc1a6a898852d81e4b40
[]
[ "license:afl-3.0" ]
https://huggingface.co/datasets/liyangbing/water/resolve/main/README.md
--- license: afl-3.0 --- this is a test
gorkaartola
null
null
null
false
1
false
gorkaartola/ZS_on_SDG_Descriptions_S1-sentence_S2-SDGtitle_Negative_Sample_Filter-Only_Targets
2022-09-06T14:51:18.000Z
null
false
6d8a794fba6e00890cdb0dffba4e1cc5edc52664
[]
[]
https://huggingface.co/datasets/gorkaartola/ZS_on_SDG_Descriptions_S1-sentence_S2-SDGtitle_Negative_Sample_Filter-Only_Targets/resolve/main/README.md
label_ids: - (0) contradiction - (2) entailment
gorkaartola
null
null
null
false
1
false
gorkaartola/ZS_on_SDG_Descriptions_S1-sentence_S2-SDGtitle_Negative_Sample_Filter-Only_Indicators
2022-09-06T14:43:39.000Z
null
false
43610fc18d73da3c4af78813f71b1c3c70c2dc44
[]
[]
https://huggingface.co/datasets/gorkaartola/ZS_on_SDG_Descriptions_S1-sentence_S2-SDGtitle_Negative_Sample_Filter-Only_Indicators/resolve/main/README.md
label_ids: - (0) contradiction - (2) entailment
gorkaartola
null
null
null
false
1
false
gorkaartola/SC-train-valid-test_SDG-Descriptions
2022-09-06T14:39:18.000Z
null
false
a8fd1c0748407b0ba5073b928ac77c2c1bed48e4
[]
[]
https://huggingface.co/datasets/gorkaartola/SC-train-valid-test_SDG-Descriptions/resolve/main/README.md
nli-label: - (0) entailment - (2) contradiction
deepmind
null
null
null
false
119
false
deepmind/code_contests
2022-07-20T11:17:09.000Z
codecontests
false
c7df7b3dfdf21d5acc550a3fc05721b8878e36ea
[]
[ "arxiv:2203.07814", "arxiv:2105.12655", "annotations_creators:found", "language_creators:found", "language:en", "license:cc-by-4.0", "multilinguality:monolingual", "size_categories:10K<n<100K", "source_datasets:original", "task_categories:translation" ]
https://huggingface.co/datasets/deepmind/code_contests/resolve/main/README.md
--- annotations_creators: - found language_creators: - found language: - en license: - cc-by-4.0 multilinguality: - monolingual size_categories: - 10K<n<100K source_datasets: - original task_categories: - translation task_ids: [] paperswithcode_id: codecontests pretty_name: CodeContests --- # Dataset Card for CodeContests ## Table of Contents - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - **Repository:** https://github.com/deepmind/code_contests/ - **Paper:** [Competition-Level Code Generation with AlphaCode](https://arxiv.org/abs/2203.07814v1) - **Leaderboard:** [Code Generation on CodeContests](https://paperswithcode.com/sota/code-generation-on-codecontests) - **Point of Contact:** [David Choi](mailto:david.hu.choi@gmail.com) ### Dataset Summary CodeContests is a competitive programming dataset for machine-learning. This dataset was used when training [AlphaCode](https://deepmind.com/blog/article/Competitive-programming-with-AlphaCode). It consists of programming problems, from a variety of sources: Site | URL | Source ----------- | --------------------------- | ------ Aizu | https://judge.u-aizu.ac.jp | [CodeNet](https://github.com/IBM/Project_CodeNet) AtCoder | https://atcoder.jp | [CodeNet](https://github.com/IBM/Project_CodeNet) CodeChef | https://www.codechef.com | [description2code](https://github.com/ethancaballero/description2code) Codeforces | https://codeforces.com | [description2code](https://github.com/ethancaballero/description2code) and Codeforces HackerEarth | https://www.hackerearth.com | [description2code](https://github.com/ethancaballero/description2code) Problems include test cases in the form of paired inputs and outputs, as well as both correct and incorrect human solutions in a variety of languages. ### Supported Tasks and Leaderboards - `translation` - the competitive programming code generation problem can be viewed as a sequence-to-sequence translation task: given a problem description 𝑋 in natural language, produce a corresponding solution 𝑌 in a programming language. The metric used for evaluation is "percentage of problems solved using 𝑛 submissions from 𝑘 samples per problem", denoted as 𝑛@𝑘. More information on the evaluation of AlphaCode can be found in Section 2.2. and Appendix A.3. of the paper. The leaderboard for this task is available [here](https://paperswithcode.com/sota/code-generation-on-codecontests). ### Languages English. ## Dataset Structure ### Data Instances A data point corresponds to a singular contest problem: ``` { 'name': '76_B. Mice', 'description': 'Modern researches has shown that a flock of hungry mice ' 'searching for a piece of...', 'public_tests': {'input': ['3 2 0 2\n0 1 3\n2 5\n'], 'output': ['1\n']}, 'private_tests': {'input': ['20 18 1 2\n' '-9999944 -9999861 -9999850 -9999763 -9999656 ' '-9999517 -9999375 -999927...', ..., '7 11 10 20\n' '6 18 32 63 66 68 87\n' '6 8 15 23 25 41 53 59 60 75 90\n'], 'output': ['2\n', ..., '1\n']}, 'generated_tests': {'input': ['7 11 10 5\n' '6 18 32 63 66 68 87\n' '6 8 15 23 25 41 53 59 60 75 90\n', ..., '7 11 10 4\n' '6 18 46 63 85 84 87\n' '6 8 15 18 25 41 53 59 60 75 90\n'], 'output': ['1\n', ..., '2\n']}, 'source': 2, 'difficulty': 8, 'solutions': {'language': [2, Ellipsis, 2], 'solution': ['#include <bits/stdc++.h>\n' 'using namespace std;\n' 'int n, m;\n' 'int data[2][100010], t[1...', ..., '#include <bits/stdc++.h>\n' 'using namespace std;\n' 'int n, m, pos[100100], food[100100...']}, 'incorrect_solutions': {'language': [2, Ellipsis, 2], 'solution': ['#include <bits/stdc++.h>\n' 'using namespace std;\n' 'vector<pair<int, int> > v[100010];...', ..., '#include <bits/stdc++.h>\n' 'using namespace std;\n' 'vector<pair<int, int> > v[100010];...']}, 'cf_contest_id': 76, 'cf_index': 'B', 'cf_points': 0.0, 'cf_rating': 2100, 'cf_tags': ['greedy', 'two pointers'], 'is_description_translated': False, 'untranslated_description': '', 'time_limit': {'seconds': 0, 'nanos': 500000000}, 'memory_limit_bytes': 256000000, 'input_file': '', 'output_file': '' } ``` ### Data Fields - `name`: The name of the contest. Note that names could agree between different sources. - `description`: A natural language description of a programming problem. - `public_tests`: Public tests are those that are available before submitting a solution, typically as part of the description itself. Represented as a paired `input` and `output` that can be used to test potential solutions. They are therefore acceptable inputs to a model. - `private_tests`: Private tests are not visible before submitting a solution, so should not be made available as inputs to a model. - `generated_tests`: Generated tests are automatically generated by modifying inputs from public and private tests and validating using known correct solutions. - `source`: The original source of the problem, with possible values including `UNKNOWN_SOURCE` (0),`CODECHEF` (1), `CODEFORCES` (2), `HACKEREARTH` (3), `CODEJAM` (4), `ATCODER` (5) and `AIZU` (6). - `difficulty`: A representation of the difficulty of the problem with possible values including `UNKNOWN_DIFFICULTY` (0), `EASY` (1), `MEDIUM` (2), `HARD` (3), `HARDER` (4), `HARDEST` (5), `EXTERNAL` (6), `A` (7), `B` (8), `C` (9), `D` (10), `E` (11), `F` (12), `G` (13), `H` (14), `I` (15), `J` (16), `K` (17), `L` (18), `M` (19), `N` (20), `O` (21), `P` (22), `Q` (23), `R` (24), `S` (25), `T` (26), `U` (27) and `V` (28). Note that different sources use different, non-comparable gradings. For Codeforces problems, `cf_rating` is a more reliable measure of difficulty when available. - `solutions`: Correct solutions to the problem. Contrast with `incorrect_solutions` below. - `incorrect_solutions`: Incorrect solutions. - `cf_contest_id`: The Contest ID. Note that Contest ID is not monotonic with respect to time. - `cf_index`: Problem index, e.g. `"A"` or `"B"` or `"C"`. - `cf_points`: Points for the problem, e.g. `1000.0` - `cf_rating`: Problem rating (difficulty), e.g. `1100` - `cf_tags`: Problem tags, e.g. `['greedy', 'math']` - `is_description_translated`: Whether the problem was translated to English. - `untranslated_description`: The untranslated description is only available for translated problems. - `time_limit`: The time limit constraint to use when executing solutions. Represented as a dictionary with two keys, `seconds` and `nanos`. This field is None if not defined. - `memory_limit_bytes`: The memory limit constraint to use when executing solutions. - `input_file`: Most problems use stdin for IO. Some problems expect specific files to be used instead. - `output_file`: Most problems use stdout for IO. Some problems expect specific files to be used instead. All tests are represented as a paired `input` and `output` that can be used to test potential solutions and all solutions and all solutions comprise a `language`, with possible values including `UNKNOWN_LANGUAGE` (0), `PYTHON` (1) (solutions written in PYTHON2), `CPP` (2), `PYTHON3` (3) and `JAVA` (4), and a `solution` string written in the `language`. The fields preceded with `cf_` denote extra meta-data for Codeforces problems. ### Data Splits The data is split into training, validation and test set. The training set contains 13328 samples, the validation set 117 samples and the test set 165 samples. ## Dataset Creation ### Curation Rationale This dataset was created for fine-tuning AlphaCode models: > Models pre-trained on GitHub can generate good code and solve simple programming problems, but as shown in Appendix B.3 they can solve very few competitive programming problems. Fine-tuning the model on a dedicated competitive programming dataset is critical for performance. ### Source Data #### Initial Data Collection and Normalization The information on the data collection and normalization procedures can found in Section 3.2. and Appendinx B.2. of the paper. #### Who are the source language producers? The problems are scraped from the following platforms: [Aizu](https://judge.u-aizu.ac.jp), [AtCoder](https://atcoder.jp ), [CodeChef](https://www.codechef.com), [Codeforces](https://codeforces.com) and [HackerEarch](https://www.hackerearth.com). Additionally, some data from the existing public competitive programming dataset Description2Code ([Caballero et al., 2016](https://github.com/ethancaballero/description2code)) and CodeNet ([(Puri et al., 2021](https://arxiv.org/pdf/2105.12655.pdf)) is mixed into the training set. ### Annotations #### Annotation process The solutions are scapred alongside the problem descriptions. #### Who are the annotators? Same as the source data creators. ### Personal and Sensitive Information [More Information Needed] ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed] ### Discussion of Biases [More Information Needed] ### Other Known Limitations [More Information Needed] ## Additional Information ### Dataset Curators Yujia Li, David Choi, Junyoung Chung, Nate Kushman, Julian Schrittwieser, Rémi Leblond, Tom Eccles, James Keeling, Felix Gimeno, Agustin Dal Lago, Thomas Hubert, Peter Choy, Cyprien de Masson d'Autume, Igor Babuschkin, Xinyun Chen, Po-Sen Huang, Johannes Welbl, Sven Gowal, Alexey Cherepanov, James Molloy, Daniel J. Mankowitz, Esme Sutherland Robson, Pushmeet Kohli, Nando de Freitas, Koray Kavukcuoglu and Oriol Vinyals. ### Licensing Information This dataset is made available under the terms of the CC BY 4.0 license ([Creative Commons Attribution 4.0 International license](https://creativecommons.org/licenses/by/4.0/legalcode)). Additional acknowledged contributions: * Codeforces materials are sourced from http://codeforces.com. * Description2Code materials are sourced from: [Description2Code Dataset](https://github.com/ethancaballero/description2code), licensed under the [MIT open source license](https://opensource.org/licenses/MIT), copyright not specified. * CodeNet materials are sourced from: [Project_CodeNet](https://github.com/IBM/Project_CodeNet), licensed under [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0), copyright not specified. ### Citation Information ```bibtex @article{li2022competition, title={Competition-Level Code Generation with AlphaCode}, author={Li, Yujia and Choi, David and Chung, Junyoung and Kushman, Nate and Schrittwieser, Julian and Leblond, R{\'e}mi and Eccles, Tom and Keeling, James and Gimeno, Felix and Dal Lago, Agustin and Hubert, Thomas and Choy, Peter and de Masson d'Autume, Cyprien and Babuschkin, Igor and Chen, Xinyun and Huang, Po-Sen and Welbl, Johannes and Gowal, Sven and Cherepanov, Alexey and Molloy, James and Mankowitz, Daniel and Sutherland Robson, Esme and Kohli, Pushmeet and de Freitas, Nando and Kavukcuoglu, Koray and Vinyals, Oriol}, journal={arXiv preprint arXiv:2203.07814}, year={2022} } ``` ### Contributions Thanks to [@mariosasko](https://github.com/mariosasko) for adding this dataset.
ufukhaman
null
null
null
false
1
false
ufukhaman/uspto_balanced_filtered_200k_ipc_patents
2022-07-19T18:50:11.000Z
null
false
da4b29c130629c1f73d718cf7fd98298fb76d984
[]
[ "annotations_creators:USPTO", "language:English", "license:mit", "multilinguality:monolingual", "size_categories:100K<n<1M", "source_datasets:original", "tags:patent", "tags:refined_patents", "tags:patent classification", "tags:uspto", "tags:ipc", "task_categories:text-classification", "task...
https://huggingface.co/datasets/ufukhaman/uspto_balanced_filtered_200k_ipc_patents/resolve/main/README.md
--- annotations_creators: - USPTO language: - English license: - mit multilinguality: - monolingual pretty_name: uspto_balanced_filtered_200k_ipc_patents size_categories: - 100K<n<1M source_datasets: - original tags: - patent - refined_patents - patent classification - uspto - ipc task_categories: - text-classification task_ids: - topic-classification ---