--- license: cc-by-4.0 metrics: - bleu4 - meteor - rouge-l - bertscore - moverscore language: en datasets: - lmqg/qg_tweetqa pipeline_tag: text2text-generation tags: - question answering widget: - text: "question: What is a person called is practicing heresy?, context: Heresy is any provocative belief or theory that is strongly at variance with established beliefs or customs. A heretic is a proponent of such claims or beliefs. Heresy is distinct from both apostasy, which is the explicit renunciation of one's religion, principles or cause, and blasphemy, which is an impious utterance or action concerning God or sacred things." example_title: "Question Answering Example 1" - text: "question: who created the post as we know it today?, context: 'So much of The Post is Ben,' Mrs. Graham said in 1994, three years after Bradlee retired as editor. 'He created it as we know it today.'— Ed O'Keefe (@edatpost) October 21, 2014" example_title: "Question Answering Example 2" model-index: - name: lmqg/t5-base-tweetqa-question-answering results: - task: name: Text2text Generation type: text2text-generation dataset: name: lmqg/qg_tweetqa type: default args: default metrics: - name: BLEU4 type: bleu4 value: 33.32 - name: ROUGE-L type: rouge-l value: 62.24 - name: METEOR type: meteor value: 35.43 - name: BERTScore type: bertscore value: 94.58 - name: MoverScore type: moverscore value: 80.07 - name: AnswerF1Score (Question Answering) type: answer_f1_score_question_answering value: 69.4 - name: AnswerExactMatch (Question Answering) type: answer_exact_match_question_answering value: 52.29 --- # Model Card of `lmqg/t5-base-tweetqa-question-answering` This model is fine-tuned version of [t5-base](https://huggingface.co./t5-base) for question answering task on the [lmqg/qg_tweetqa](https://huggingface.co./datasets/lmqg/qg_tweetqa) (dataset_name: default) via [`lmqg`](https://github.com/asahi417/lm-question-generation). ### Overview - **Language model:** [t5-base](https://huggingface.co./t5-base) - **Language:** en - **Training data:** [lmqg/qg_tweetqa](https://huggingface.co./datasets/lmqg/qg_tweetqa) (default) - **Online Demo:** [https://autoqg.net/](https://autoqg.net/) - **Repository:** [https://github.com/asahi417/lm-question-generation](https://github.com/asahi417/lm-question-generation) - **Paper:** [https://arxiv.org/abs/2210.03992](https://arxiv.org/abs/2210.03992) ### Usage - With [`lmqg`](https://github.com/asahi417/lm-question-generation#lmqg-language-model-for-question-generation-) ```python from lmqg import TransformersQG # initialize model model = TransformersQG(language="en", model="lmqg/t5-base-tweetqa-question-answering") # model prediction answers = model.answer_q(list_question="What is a person called is practicing heresy?", list_context=" Heresy is any provocative belief or theory that is strongly at variance with established beliefs or customs. A heretic is a proponent of such claims or beliefs. Heresy is distinct from both apostasy, which is the explicit renunciation of one's religion, principles or cause, and blasphemy, which is an impious utterance or action concerning God or sacred things.") ``` - With `transformers` ```python from transformers import pipeline pipe = pipeline("text2text-generation", "lmqg/t5-base-tweetqa-question-answering") output = pipe("question: What is a person called is practicing heresy?, context: Heresy is any provocative belief or theory that is strongly at variance with established beliefs or customs. A heretic is a proponent of such claims or beliefs. Heresy is distinct from both apostasy, which is the explicit renunciation of one's religion, principles or cause, and blasphemy, which is an impious utterance or action concerning God or sacred things.") ``` ## Evaluation - ***Metric (Question Answering)***: [raw metric file](https://huggingface.co./lmqg/t5-base-tweetqa-question-answering/raw/main/eval/metric.first.answer.paragraph_question.answer.lmqg_qg_tweetqa.default.json) | | Score | Type | Dataset | |:-----------------|--------:|:--------|:-------------------------------------------------------------------| | AnswerExactMatch | 52.29 | default | [lmqg/qg_tweetqa](https://huggingface.co./datasets/lmqg/qg_tweetqa) | | AnswerF1Score | 69.4 | default | [lmqg/qg_tweetqa](https://huggingface.co./datasets/lmqg/qg_tweetqa) | | BERTScore | 94.58 | default | [lmqg/qg_tweetqa](https://huggingface.co./datasets/lmqg/qg_tweetqa) | | Bleu_1 | 57.07 | default | [lmqg/qg_tweetqa](https://huggingface.co./datasets/lmqg/qg_tweetqa) | | Bleu_2 | 48.17 | default | [lmqg/qg_tweetqa](https://huggingface.co./datasets/lmqg/qg_tweetqa) | | Bleu_3 | 39.78 | default | [lmqg/qg_tweetqa](https://huggingface.co./datasets/lmqg/qg_tweetqa) | | Bleu_4 | 33.32 | default | [lmqg/qg_tweetqa](https://huggingface.co./datasets/lmqg/qg_tweetqa) | | METEOR | 35.43 | default | [lmqg/qg_tweetqa](https://huggingface.co./datasets/lmqg/qg_tweetqa) | | MoverScore | 80.07 | default | [lmqg/qg_tweetqa](https://huggingface.co./datasets/lmqg/qg_tweetqa) | | ROUGE_L | 62.24 | default | [lmqg/qg_tweetqa](https://huggingface.co./datasets/lmqg/qg_tweetqa) | ## Training hyperparameters The following hyperparameters were used during fine-tuning: - dataset_path: lmqg/qg_tweetqa - dataset_name: default - input_types: ['paragraph_question'] - output_types: ['answer'] - prefix_types: None - model: t5-base - max_length: 512 - max_length_output: 32 - epoch: 10 - batch: 32 - lr: 0.0001 - fp16: False - random_seed: 1 - gradient_accumulation_steps: 2 - label_smoothing: 0.15 The full configuration can be found at [fine-tuning config file](https://huggingface.co./lmqg/t5-base-tweetqa-question-answering/raw/main/trainer_config.json). ## Citation ``` @inproceedings{ushio-etal-2022-generative, title = "{G}enerative {L}anguage {M}odels for {P}aragraph-{L}evel {Q}uestion {G}eneration", author = "Ushio, Asahi and Alva-Manchego, Fernando and Camacho-Collados, Jose", booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing", month = dec, year = "2022", address = "Abu Dhabi, U.A.E.", publisher = "Association for Computational Linguistics", } ```