text stringlengths 0 164k |
|---|
<s>[INST] Minimally Supervised Learning of Affective Events Using Discourse Relations [/INST] Affective events BIBREF0 are events that typically affect people in positive or negative ways For example getting money and playing sports are usually positive to the experiencers catching cold and losing ones wallet are negat... |
<s>[INST] PO-EMO: Conceptualization, Annotation, and Modeling of Aesthetic Emotions in German and English Poetry [/INST] 11em 111em 1111em Thomas Haider13 Steffen Eger2 Evgeny Kim3 Roman Klinger3 Winfried Menninghaus1 1Department of Language and Literature Max Planck Institute for Empirical Aesthetics 2NLLG Department ... |
<s>[INST] Community Identity and User Engagement in a Multi-Community Landscape [/INST] If each city is like a game of chess the day when I have learned the rules I shall finally possess my empire even if I shall never succeed in knowing all the cities it contains Italo Calvino Invisible Cities A communitys identityd... |
<s>[INST] Question Answering based Clinical Text Structuring Using Pre-trained Language Model [/INST] Clinical text structuring CTS is a critical task for fetching medical research data from electronic health records EHRs where structural patient medical data such as whether the patient has specific symptoms diseases o... |
<s>[INST] Progress and Tradeoffs in Neural Language Models [/INST] Deep learning has unquestionably advanced the state of the art in many natural language processing tasks from syntactic dependency parsing BIBREF0 to namedentity recognition BIBREF1 to machine translation BIBREF2 The same certainly applies to language ... |
mathbf Z tanh mathbf Wz cdot mathbf X |
mathbf F sigma mathbf Wf cdot mathbf X |
mathbf O sigma mathbf Wo cdot mathbf X |
where sigma denotes the sigmoid function cdot represents masked convolution across time and mathbf Wlbrace z f orbrace in mathbb Rm times k times r are convolution weights with k input channels m output channels and a window size of r In the recurrent pooling layer the convolution outputs are combined sequentiall... |
mathbf ct mathbf ft odot mathbf ct1 1 |
mathbf ft odot mathbf zt |
mathbf ht mathbf ot odot mathbf ct |
Multiple QRNN layers can be stacked for deeper hierarchical representation with the output mathbf h1t being fed as the input into the subsequent layer In language modeling a fourlayer QRNN is a standard architecture BIBREF11 PerplexityRecall Scale Wordlevel perplexity does not have a strictly monotonic relationship ... |
<s>[INST] Stay On-Topic: Generating Context-specific Fake Restaurant Reviews [/INST] Automatically generated fake reviews have only recently become natural enough to fool human readers Yao et al BIBREF0 use a deep neural network a socalled 2layer LSTM BIBREF1 to generate fake reviews and concluded that these fake revi... |
<s>[INST] Saliency Maps Generation for Automatic Text Summarization [/INST] Ever since the LIME algorithm BIBREF0 explanation techniques focusing on finding the importance of input features in regard of a specific prediction have soared and we now have many ways of finding saliency maps also called heatmaps because of... |
Rileftarrow jl l1 dfracwirightarrow jll1textbf zli dfracepsilon textrm signtextbf zl1j textbf bl1jDltextbf zl1j epsilon textrm signtextbf zl1j Rjl1 |
endsplit Eq 7 where wirightarrow jll1 is the networks weight parameter set during training textbf bl1j is the bias for neuron j of layer l1 textbf zli is the activation of neuron i on layer l epsilon is the stabilizing term set to 000001 and Dl is the dimension of the l th layer The relevance of a neuron is then ... |
<s>[INST] Probabilistic Bias Mitigation in Word Embeddings [/INST] Word embeddings or vector representations of words are an important component of Natural Language Processing NLP models and necessary for many downstream tasks However word embeddings including embeddings commonly deployed for public use have been shown... |
<s>[INST] Massive vs. Curated Word Embeddings for Low-Resourced Languages. The Case of Yor\`ub\'a and Twi [/INST] In recent years word embeddings BIBREF0 BIBREF1 BIBREF2 have been proven to be very useful for training downstream natural language processing NLP tasks Moreover contextualized embeddings BIBREF3 BIBREF4 ha... |
<s>[INST] Is there Gender bias and stereotype in Portuguese Word Embeddings? [/INST] Recently the transformative potential of machine learning ML has propelled ML into the forefront of mainstream media In Brazil the use of such technique has been widely diffused gaining more space Thus it is used to search for patterns... |
<s>[INST] Citation Data of Czech Apex Courts [/INST] Analysis of the way court decisions refer to each other provides us with important insights into the decisionmaking process at courts This is true both for the common law courts and for their counterparts in the countries belonging to the continental legal system Cit... |
<s>[INST] LAXARY: A Trustworthy Explainable Twitter Analysis Model for Post-Traumatic Stress Disorder Assessment [/INST] Combat veterans diagnosed with PTSD are substantially more likely to engage in a number of high risk activities including engaging in interpersonal violence attempting suicide committing suicide bing... |
<s>[INST] Comprehensive Named Entity Recognition on CORD-19 with Distant or Weak Supervision [/INST] Coronavirus disease 2019 COVID19 is an infectious disease caused by severe acute respiratory syndrome coronavirus 2 SARSCoV2 The disease was first identified in 2019 in Wuhan Central China and has since spread globally ... |
<s>[INST] UniSent: Universal Adaptable Sentiment Lexica for 1000+ Languages [/INST] Sentiment classification is an important task which requires either word level or document level sentiment annotations Such resources are available for at most 136 languages BIBREF0 preventing accurate sentiment classification in a low... |
<s>[INST] Word Sense Disambiguation for 158 Languages using Word Embeddings Only [/INST] 11em 111em 1111em rurussian 1Skolkovo Institute of Science and Technology Moscow Russia vlogachevaskoltechru 2Ural Federal University Yekaterinburg Russia 3Universitt Hamburg Hamburg Germany 4Universitt Mannheim Mannheim Germany 5... |
<s>[INST] Spoken Language Identification using ConvNets [/INST] Language Identification LI is a problem which involves classifying the language being spoken by a speaker LI systems can be used in call centers to route international calls to an operator who is fluent in that identified language BIBREF0 In speechbased as... |
<s>[INST] Unsupervised Bilingual Lexicon Induction from Mono-lingual Multimodal Data [/INST] The bilingual lexicon induction task aims to automatically build word translation dictionaries across different languages which is beneficial for various natural language processing tasks such as crosslingual information retrie... |
<s>[INST] AraNet: A Deep Learning Toolkit for Arabic Social Media [/INST] The proliferation of social media has made it possible to study large online communities at scale thus making important discoveries that can facilitate decision making guide policies improve health and wellbeing aid disaster response etc The wide... |
<s>[INST] Generative Adversarial Nets for Multiple Text Corpora [/INST] Generative adversarial nets GAN Goodfellow et al 2014 belong to a class of generative models which are trainable and can generate artificial data examples similar to the existing ones In a GAN model there are two submodels simultaneously trained a ... |
<s>[INST] Stacked DeBERT: All Attention in Incomplete Data for Text Classification [/INST] Understanding a users intent and sentiment is of utmost importance for current intelligent chatbots to respond appropriately to human requests However current systems are not able to perform to their best capacity when presented ... |
<s>[INST] Gunrock: A Social Bot for Complex and Engaging Long Conversations [/INST] Amazon Alexa Prize BIBREF0 provides a platform to collect real humanmachine conversation data and evaluate performance on speechbased social conversational systems Our system Gunrock BIBREF1 addresses several limitations of prior chatbo... |
<s>[INST] Towards Detection of Subjective Bias using Contextualized Word Embeddings [/INST] In natural language subjectivity refers to the aspects of communication used to express opinions evaluations and speculationsBIBREF0 often influenced by ones emotional state and viewpoints Writers and editors of texts like news ... |
<s>[INST] Sentence-Level Fluency Evaluation: References Help, But Can Be Spared! [/INST] Producing sentences which are perceived as natural by a human addresseea property which we will denote as fluency throughout this paper is a crucial goal of all natural language generation NLG systems it makes interactions more nat... |
textrm ii textrm He is a citizen of Tuvalunonumber Eq 11 Given that both sentences are of equal length and assuming that France appears more often in a given LM training set than Tuvalu the lengthnormalized logprobability of sentence i under the LM would most likely be higher than that of sentence ii However sin... |
<s>[INST] An empirical study on the effectiveness of images in Multimodal Neural Machine Translation [/INST] In machine translation neural networks have attracted a lot of research attention Recently the attentionbased encoderdecoder framework BIBREF0 BIBREF1 has been largely adopted In this approach Recurrent Neural ... |
<s>[INST] Unsupervised Machine Commenting with Neural Variational Topic Model [/INST] Making article comments is a fundamental ability for an intelligent machine to understand the article and interact with humans It provides more challenges because commenting requires the abilities of comprehending the article summariz... |
<s>[INST] Enriching BERT with Knowledge Graph Embeddings for Document Classification [/INST] With everincreasing amounts of data available there is an increase in the need to offer tooling to speed up processing and eventually making sense of this data Because fullyautomated tools to extract meaning from any given inpu... |
<s>[INST] Diachronic Topics in New High German Poetry [/INST] The Digital Library in the TextGrid Repository represents an extensive collection of German texts in digital form BIBREF3 It was mined from httpzenoorg and covers a time period from the mid 16th century up to the first decades of the 20th century It contains... |
<s>[INST] Important Attribute Identification in Knowledge Graph [/INST] Knowledge graphKG has been proposed for several years and its most prominent application is in web search for example Google search triggers a certain entity card when a users query matches or mentions an entity based on some statistical model The ... |
<s>[INST] Diversity, Density, and Homogeneity: Quantitative Characteristic Metrics for Text Collections [/INST] Characteristic metrics are a set of unsupervised measures that quantitatively describe or summarize the properties of a data collection These metrics generally do not use groundtruth labels and only measure t... |
<s>[INST] What Drives the International Development Agenda? An NLP Analysis of the United Nations General Debate 1970-2016 [/INST] Decisions made in international organisations are fundamental to international development efforts and initiatives It is in these global governance arenas that the rules of the global econo... |
<s>[INST] QnAMaker: Data to Bot in 2 Minutes [/INST] QnAMaker aims to simplify the process of bot creation by extracting QuestionAnswer QA pairs from data given by users into a Knowledge Base KB and providing a conversational layer over it KB here refers to one instance of azure search index where the extracted QA are ... |
<s>[INST] A simple discriminative training method for machine translation with large-scale features [/INST] Since Och BIBREF0 proposed minimum error rate training MERT to exactly optimize objective evaluation measures MERT has become a standard model tuning technique in statistical machine translation SMT Though MERT p... |
<s>[INST] Improving Spoken Language Understanding By Exploiting ASR N-best Hypotheses [/INST] Currently voicecontrolled smart devices are widely used in multiple areas to fulfill various tasks eg playing music acquiring weather information and booking tickets The SLU system employs several modules to enable the underst... |
<s>[INST] DisSim: A Discourse-Aware Syntactic Text Simplification Frameworkfor English and German [/INST] We developed a syntactic text simplification TS approach that can be used as a preprocessing step to facilitate and improve the performance of a wide range of artificial intelligence AI tasks such as Machine Transl... |
<s>[INST] Learning Word Embeddings from the Portuguese Twitter Stream: A Study of some Practical Aspects [/INST] Word embeddings have great practical importance since they can be used as precomputed highdensity features to ML models significantly reducing the amount of training data required in a variety of NLP tasks H... |
<s>[INST] Procedural Reasoning Networks for Understanding Multimodal Procedures [/INST] A great deal of commonsense knowledge about the world we live is procedural in nature and involves steps that show ways to achieve specific goals Understanding and reasoning about procedural texts eg cooking recipes howto guides sci... |
<s>[INST] Active Learning for Chinese Word Segmentation in Medical Text [/INST] Electronic health records EHRs systematically collect patients clinical information such as health profiles histories of present illness past medical histories examination results and treatment plans BIBREF0 By analyzing EHRs many useful i... |
<s>[INST] InScript: Narrative texts annotated with script information [/INST] A script is a standardized sequence of events that describes some stereotypical human activity such as going to a restaurant or visiting a doctor BIBREF0 Script events describe an actionactivity along with the involved participants For examp... |
<s>[INST] Investigating Robustness and Interpretability of Link Prediction via Adversarial Modifications [/INST] Knowledge graphs KG play a critical role in many realworld applications such as search structured data management recommendations and question answering Since KGs often suffer from incompleteness and noise i... |
For adversarial modifications on KGs we first define the space of possible modifications For a target triple langle s r orangle we constrain the possible triples that we can remove or inject to be in the form of langle sprime rprime orangle ie sprime and rprime may be different from the target but the object i... |
<s>[INST] Learning Supervised Topic Models for Classification and Regression from Crowds [/INST] Topic models such as latent Dirichlet allocation LDA allow us to analyze large collections of documents by revealing their underlying themes or topics and how each document exhibits them BIBREF0 Therefore it is not surpris... |
<s>[INST] CrossWOZ: A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset [/INST] Recently there have been a variety of taskoriented dialogue models thanks to the prosperity of neural architectures BIBREF0 BIBREF1 BIBREF2 BIBREF3 BIBREF4 BIBREF5 However the research is still largely limited by the availabil... |
<s>[INST] BERTRAM: Improved Word Embeddings Have Big Impact on Contextualized Model Performance [/INST] As traditional word embedding algorithms BIBREF1 are known to struggle with rare words several techniques for improving their representations have been proposed over the last few years These approaches exploit either... |
<s>[INST] Joint Entity Linking with Deep Reinforcement Learning [/INST] Entity Linking EL which is also called Entity Disambiguation ED is the task of mapping mentions in text to corresponding entities in a given knowledge Base KB This task is an important and challenging stage in text understanding because mentions ar... |
JTheta mathbb Est atsim PTheta st atRs1a1sLaL |
sum tsum api Theta asRat |
endsplit Eq 19 Where PTheta st at is the state transfer function pi Theta as indicates the probability of taking action a under the state s Rat is the expected reward of action a at time step t According to REINFORCE policy gradient algorithm BIBREF13 we update the policy gradient by the way of equation 9 Theta ... |
<s>[INST] Classification Betters Regression in Query-based Multi-document Summarisation Techniques for Question Answering: Macquarie University at BioASQ7b [/INST] The BioASQ Challenge includes a question answering task Phase B part B where the aim is to find the ideal answer that is an answer that would normally be g... |
<s>[INST] Marrying Universal Dependencies and Universal Morphology [/INST] The two largest standardized crosslingual datasets for morphological annotation are provided by the Universal Dependencies BIBREF1 and Universal Morphology BIBREF2 BIBREF3 projects Each projects data are annotated according to its own crossling... |
<s>[INST] Towards Multimodal Emotion Recognition in German Speech Events in Cars using Transfer Learning [/INST] Automatic emotion recognition is commonly understood as the task of assigning an emotion to a predefined instance for example an utterance as audio signal an image for instance with a depicted face or a text... |
<s>[INST] Revisiting Low-Resource Neural Machine Translation: A Case Study [/INST] While neural machine translation NMT has achieved impressive performance in highresource data conditions becoming dominant in the field BIBREF0 BIBREF1 BIBREF2 recent research has argued that these models are highly datainefficient an... |
<s>[INST] Facilitating on-line opinion dynamics by mining expressions of causation. The case of climate change debates on The Guardian [/INST] Over the past two decades the rise of social media and the digitization of news and discussion platforms have radically transformed how individuals and groups create process and... |
<s>[INST] "Hinglish"Language -- Modeling a Messy Code-Mixed Language [/INST] Hinglish is a linguistic blend of Hindi very widely spoken language in India and English an associate language of urban areas and is spoken by upwards of 350 million people in India While the name is based on the Hindi language it does not ref... |
<s>[INST] How Language-Neutral is Multilingual BERT? [/INST] Multilingual BERT mBERT BIBREF0 is gaining popularity as a contextual representation for various multilingual tasks such as dependency parsing BIBREF1 BIBREF2 crosslingual natural language inference XNLI or namedentity recognition NER BIBREF3 BIBREF4 BIBREF5 ... |
<s>[INST] CAiRE: An End-to-End Empathetic Chatbot [/INST] Empathetic chatbots are conversational agents that can understand user emotions and respond appropriately Incorporating empathy into the dialogue system is essential to achieve better humanrobot interaction because naturally humans express and perceive emotion i... |
<s>[INST] Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness? [/INST] Fueled by recent advances in deeplearning and language processing NLP systems are increasingly being used for prediction and decisionmaking in many fields BIBREF0 including sensitive ones such as health comme... |
<s>[INST] Interpreting Recurrent and Attention-Based Neural Models: a Case Study on Natural Language Inference [/INST] Deep learning has achieved tremendous success for many NLP tasks However unlike traditional methods that provide optimized weights for human understandable features the behavior of deep learning models... |
<s>[INST] Exploring Question Understanding and Adaptation in Neural-Network-Based Question Answering [/INST] Enabling computers to understand given documents and answer questions about their content has recently attracted intensive interest including but not limited to the efforts as in BIBREF0 BIBREF1 BIBREF2 BIBRE... |
mathbf DcjtextBiGRUmathbf Dejjforall j in 1 dots M Eq 5 A BiGRU runs a forward and backward GRU on a sequence starting from the left and the right end respectively By concatenating the hidden states of these two GRUs for each word we obtain the a representation for a question or document mathbf Qc in mathbb R Ntime... |
mathbf ht mathbf ot circ tanh mathbf ct |
mathbf ot sigma mathbf Wo mathbf xt mathbf UoL mathbf ht1L mathbf UoR mathbf ht1R mathbf ct mathbf ftL circ mathbf ct1L mathbf ftR circ mathbf ct1R mathbf it circ mathbf ut mathbf ftL sigma mathbf Wf mathbf xt mathbf UfLL mathbf ht1L mathbf UfLR mathbf ht1R |
mathbf ftR sigma mathbf Wf mathbf xt mathbf UfRL mathbf ht1L mathbf UfRR mathbf ht1R mathbf it sigma mathbf Wi mathbf xt mathbf UiL mathbf ht1L mathbf UiR mathbf ht1R mathbf ut tanh mathbf Wc mathbf xt mathbf UcL mathbf ht1L mathbf UcR mathbf ht1R Eq 31 where sigma is the sigmoid function circ is the elem... |
<s>[INST] SUM-QE: a BERT-based Summary Quality Estimation Model [/INST] Quality Estimation QE is a term used in machine translation MT to refer to methods that measure the quality of automatically translated text without relying on human references BIBREF0 BIBREF1 In this study we address QE for summarization Our propo... |
<s>[INST] Learning Hierarchy-Aware Knowledge Graph Embeddings for Link Prediction [/INST] Knowledge graphs are usually collections of factual tripleshead entity relation tail entity which represent human knowledge in a structured way In the past few years we have witnessed the great achievement of knowledge graphs in m... |
<s>[INST] Machine Translation from Natural Language to Code using Long-Short Term Memory [/INST] Removing computerhuman language barrier is an inevitable advancement researchers are thriving to achieve for decades One of the stages of this advancement will be coding through natural human language instead of traditional... |
<s>[INST] A Survey and Taxonomy of Adversarial Neural Networks for Text-to-Image Synthesis [/INST] GANs and the variations that are now being proposed is the most interesting idea in the last 10 years in ML in my opinion 2016 Yann LeCun A picture is worth a thousand words While written text provide efficient effectiv... |
<s>[INST] Gating Mechanisms for Combining Character and Word-level Word Representations: An Empirical Study [/INST] Incorporating subword structures like substrings morphemes and characters to the creation of word representations significantly increases their quality as reflected both by intrinsic metrics and performan... |
<s>[INST] Effective Modeling of Encoder-Decoder Architecture for Joint Entity and Relation Extraction [/INST] Distantlysupervised information extraction systems extract relation tuples with a set of predefined relations from text Traditionally researchers BIBREF0 BIBREF1 BIBREF2 use pipeline approaches where a named en... |
<s>[INST] Learning to Rank Scientific Documents from the Crowd [/INST] blockI1em blocki1em Learning to Rank Scientific Documents from the CrowdLearning to Rank Scientific Documents from the Crowd 4 11 The number of biomedical research papers published has increased dramatically in recent years As of October 2016 PubM... |
<s>[INST] Exploiting Deep Learning for Persian Sentiment Analysis [/INST] In recent years social media forums blogs and other forms of online communication tools have radically affected everyday life especially how people express their opinions and comments The extraction of useful information such as peoples opinion a... |
<s>[INST] Talk the Walk: Navigating New York City through Grounded Dialogue [/INST] 0pt00303 0pt003003 0pt003003 We introduce Talk The Walk the first largescale dialogue dataset grounded in action and perception The task involves two agents a guide and a tourist that communicate via natural language in order to achie... |
<s>[INST] Real-time Claim Detection from News Articles and Retrieval of Semantically-Similar Factchecks [/INST] In recent years the spread of misinformation has become a growing concern for researchers and the public at large BIBREF1 Researchers at MIT found that social media users are more likely to share false infor... |
<s>[INST] RC-QED: Evaluating Natural Language Derivations in Multi-Hop Reading Comprehension [/INST] Reading comprehension RC has become a key benchmark for natural language understanding NLU systems and a large number of datasets are now available BIBREF0 BIBREF1 BIBREF2 However these datasets suffer from annotation a... |
<s>[INST] Event Outcome Prediction using Sentiment Analysis and Crowd Wisdom in Microblog Feeds [/INST] Over the past few years microblogs have become one of the most popular online social networks Microblogging websites have evolved to become a source of varied kinds of information This is due to the nature of microbl... |
<s>[INST] Learning High-order Structural and Attribute information by Knowledge Graph Attention Networks for Enhancing Knowledge Graph Embedding [/INST] In the past decade many largescale Knowledge Graphs KGs such as Freebase BIBREF0 DBpedia BIBREF1 and YAGO BIBREF2 have been built to represent human complex knowledge ... |
<s>[INST] A Computational Approach to Automatic Prediction of Drunk Texting [/INST] The ubiquity of communication devices has made social media highly accessible The content on these media reflects a users daytoday activities This includes content created under the influence of alcohol In popular culture this has been ... |
<s>[INST] Answering Complex Questions Using Open Information Extraction [/INST] Effective question answering QA systems have been a longstanding quest of AI research Structured curated KBs have been used successfully for this task BIBREF0 BIBREF1 However these KBs are expensive to build and typically domainspecific A... |
textit tfx q1 textmd if x in q textit idfx log1 Nnx |
textit tfidft qsum x in tcap q idfx |
where N is the number of tuples in the KB and nx are the number of tuples containing x We normalize the tfidf score by the number of tokens in t and q We finally take the 50 topscoring tuples Tqa Onthefly tuples from text To handle questions from new domains not covered by the training set we extract additional t... |
<s>[INST] An Unsupervised Word Sense Disambiguation System for Under-Resourced Languages [/INST] Word sense disambiguation WSD is a natural language processing task of identifying the particular word senses of polysemous words used in a sentence Recently a lot of attention was paid to the problem of WSD for the Russian... |
<s>[INST] Quasar: Datasets for Question Answering by Search and Reading [/INST] Factoid Question Answering QA aims to extract answers from an underlying knowledge source to information seeking questions posed in natural language Depending on the knowledge source available there are two main approaches for factoid QA St... |
<s>[INST] Error Analysis for Vietnamese Named Entity Recognition on Deep Neural Network Models [/INST] Named Entity Recognition NER is one of information extraction subtasks that is responsible for detecting entity elements from raw text and can determine the category in which the element belongs these categories inclu... |
<s>[INST] Recurrent Neural Network Encoder with Attention for Community Question Answering [/INST] Community question answering cQA is a paradigm that provides forums for users to ask or answer questions on any topic with barely any restrictions In the past decade these websites have attracted a great number of users a... |
xt03em |
ht103em |
endbmatrix |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.