| | --- |
| | language: de |
| | datasets: |
| | - deepset/germanquad |
| | license: mit |
| | thumbnail: https://thumb.tildacdn.com/tild3433-3637-4830-a533-353833613061/-/resize/720x/-/format/webp/germanquad.jpg |
| | tags: |
| | - exbert |
| | --- |
| | |
| | # gelectra-base distilled for Extractive QA |
| |
|
| | ## Overview |
| | **Language model:** gelectra-base-germanquad-distilled |
| | **Language:** German |
| | **Training data:** GermanQuAD train set (~ 12MB) |
| | **Eval data:** GermanQuAD test set (~ 5MB) |
| | **Code:** See [an example extractive QA pipeline built with Haystack](https://haystack.deepset.ai/tutorials/34_extractive_qa_pipeline) |
| | **Infrastructure**: 1x V100 GPU |
| | **Published**: Apr 21st, 2021 |
| |
|
| | ## Details |
| | - We trained a German question answering model with a gelectra-base model as its basis. |
| | - The dataset is GermanQuAD, a new, German language dataset, which we hand-annotated and published [online](https://deepset.ai/germanquad). |
| | - The training dataset is one-way annotated and contains 11518 questions and 11518 answers, while the test dataset is three-way annotated so that there are 2204 questions and with 2204·3−76 = 6536answers, because we removed 76 wrong answers. |
| | - In addition to the annotations in GermanQuAD, haystack's distillation feature was used for training. deepset/gelectra-large-germanquad was used as the teacher model. |
| |
|
| | See https://deepset.ai/germanquad for more details and dataset download in SQuAD format. |
| |
|
| | ## Hyperparameters |
| | ``` |
| | batch_size = 24 |
| | n_epochs = 6 |
| | max_seq_len = 384 |
| | learning_rate = 3e-5 |
| | lr_schedule = LinearWarmup |
| | embeds_dropout_prob = 0.1 |
| | temperature = 2 |
| | distillation_loss_weight = 0.75 |
| | ``` |
| |
|
| |
|
| | ## Usage |
| |
|
| | ### In Haystack |
| | Haystack is an AI orchestration framework to build customizable, production-ready LLM applications. You can use this model in Haystack to do extractive question answering on documents. |
| | To load and run the model with [Haystack](https://github.com/deepset-ai/haystack/): |
| | ```python |
| | # After running pip install haystack-ai "transformers[torch,sentencepiece]" |
| | |
| | from haystack import Document |
| | from haystack.components.readers import ExtractiveReader |
| | |
| | docs = [ |
| | Document(content="Python is a popular programming language"), |
| | Document(content="python ist eine beliebte Programmiersprache"), |
| | ] |
| | |
| | reader = ExtractiveReader(model="deepset/gelectra-base-germanquad-distilled") |
| | reader.warm_up() |
| | |
| | question = "What is a popular programming language?" |
| | result = reader.run(query=question, documents=docs) |
| | # {'answers': [ExtractedAnswer(query='What is a popular programming language?', score=0.5740374326705933, data='python', document=Document(id=..., content: '...'), context=None, document_offset=ExtractedAnswer.Span(start=0, end=6),...)]} |
| | ``` |
| | For a complete example with an extractive question answering pipeline that scales over many documents, check out the [corresponding Haystack tutorial](https://haystack.deepset.ai/tutorials/34_extractive_qa_pipeline). |
| |
|
| | ### In Transformers |
| | ```python |
| | from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline |
| | |
| | model_name = "deepset/gelectra-base-germanquad-distilled" |
| | |
| | # a) Get predictions |
| | nlp = pipeline('question-answering', model=model_name, tokenizer=model_name) |
| | QA_input = { |
| | 'question': 'Why is model conversion important?', |
| | 'context': 'The option to convert models between FARM and transformers gives freedom to the user and let people easily switch between frameworks.' |
| | } |
| | res = nlp(QA_input) |
| | |
| | # b) Load model & tokenizer |
| | model = AutoModelForQuestionAnswering.from_pretrained(model_name) |
| | tokenizer = AutoTokenizer.from_pretrained(model_name) |
| | ``` |
| |
|
| | ## Performance |
| | We evaluated the extractive question answering performance on our GermanQuAD test set. |
| | Model types and training data are included in the model name. |
| | For finetuning XLM-Roberta, we use the English SQuAD v2.0 dataset. |
| | The GELECTRA models are warm started on the German translation of SQuAD v1.1 and finetuned on \\\\germanquad. |
| | The human baseline was computed for the 3-way test set by taking one answer as prediction and the other two as ground truth. |
| | ``` |
| | "exact": 62.4773139745916 |
| | "f1": 80.9488017070188 |
| | ``` |
| |  |
| |
|
| | ## Authors |
| | - Timo Möller: `timo.moeller [at] deepset.ai` |
| | - Julian Risch: `julian.risch [at] deepset.ai` |
| | - Malte Pietsch: `malte.pietsch [at] deepset.ai` |
| | - Michel Bartels: `michel.bartels [at] deepset.ai` |
| |
|
| | ## About us |
| |
|
| | <div class="grid lg:grid-cols-2 gap-x-4 gap-y-3"> |
| | <div class="w-full h-40 object-cover mb-2 rounded-lg flex items-center justify-center"> |
| | <img alt="" src="https://raw.githubusercontent.com/deepset-ai/.github/main/deepset-logo-colored.png" class="w-40"/> |
| | </div> |
| | <div class="w-full h-40 object-cover mb-2 rounded-lg flex items-center justify-center"> |
| | <img alt="" src="https://raw.githubusercontent.com/deepset-ai/.github/main/haystack-logo-colored.png" class="w-40"/> |
| | </div> |
| | </div> |
| | |
| | [deepset](http://deepset.ai/) is the company behind the production-ready open-source AI framework [Haystack](https://haystack.deepset.ai/). |
| |
|
| | Some of our other work: |
| | - [Distilled roberta-base-squad2 (aka "tinyroberta-squad2")](https://huggingface.co/deepset/tinyroberta-squad2) |
| | - [German BERT](https://deepset.ai/german-bert), [GermanQuAD and GermanDPR](https://deepset.ai/germanquad), [German embedding model](https://huggingface.co/mixedbread-ai/deepset-mxbai-embed-de-large-v1) |
| | - [deepset Cloud](https://www.deepset.ai/deepset-cloud-product), [deepset Studio](https://www.deepset.ai/deepset-studio) |
| |
|
| | ## Get in touch and join the Haystack community |
| |
|
| | <p>For more info on Haystack, visit our <strong><a href="https://github.com/deepset-ai/haystack">GitHub</a></strong> repo and <strong><a href="https://docs.haystack.deepset.ai">Documentation</a></strong>. |
| |
|
| | We also have a <strong><a class="h-7" href="https://haystack.deepset.ai/community">Discord community open to everyone!</a></strong></p> |
| |
|
| | [Twitter](https://twitter.com/Haystack_AI) | [LinkedIn](https://www.linkedin.com/company/deepset-ai/) | [Discord](https://haystack.deepset.ai/community) | [GitHub Discussions](https://github.com/deepset-ai/haystack/discussions) | [Website](https://haystack.deepset.ai/) | [YouTube](https://www.youtube.com/@deepset_ai) |
| |
|
| | By the way: [we're hiring!](http://www.deepset.ai/jobs) |
