--- license: cc-by-4.0 metrics: - bleu4 - meteor - rouge-l - bertscore - moverscore language: zh datasets: - lmqg/qg_zhquad pipeline_tag: text2text-generation tags: - question generation - answer extraction widget: - text: "generate question: 南安普敦的警察服务由汉普郡警察提供。南安普敦行动的主要基地是一座新的八层专用建筑，造价3000万英镑。该建筑位于南路，2011年启用，靠近 南安普敦中央 火车站。此前，南安普顿市中心的行动位于市民中心西翼，但由于设施老化，加上计划在旧警察局和地方法院建造一座新博物馆，因此必须搬迁。在Portswood、Banister Park、Hille和Shirley还有其他警察局，在南安普顿中央火车站还有一个英国交通警察局。" example_title: "Question Generation Example 1" - text: "generate question: 芝加哥大学的 1960—61 集团理论年汇集了Daniel Gorenstein、John G. Thompson和Walter Feit等团体理论家，奠定了一个合作的基础，借助于其他众多数学家的输入，1982中对所有有限的简单群进行了分类。这个项目的规模超过了以往的数学研究，无论是证明的长度还是研究人员的数量。目前正在进行研究，以简化这一分类的证明。如今，群论仍然是一个非常活跃的数学分支，影响着许多其他领域" example_title: "Question Generation Example 2" - text: "extract answers: 南安普敦的警察服务由汉普郡警察提供。 南安普敦行动的主要基地是一座新的八层专用建筑，造价3000万英镑。 该建筑位于南路，2011年启用，靠近 南安普敦中央 火车站。 此前，南安普顿市中心的行动位于市民中心西翼，但由于设施老化，加上计划在旧警察局和地方法院建造一座新博物馆，因此必须搬迁。 在Portswood、Banister Park、Hille和Shirley还有其他警察局，在南安普顿中央火车站还有一个英国交通警察局。" example_title: "Answer Extraction Example 1" model-index: - name: lmqg/mt5-base-zhquad-qg-ae results: - task: name: Text2text Generation type: text2text-generation dataset: name: lmqg/qg_zhquad type: default args: default metrics: - name: BLEU4 (Question Generation) type: bleu4_question_generation value: 14.63 - name: ROUGE-L (Question Generation) type: rouge_l_question_generation value: 34.07 - name: METEOR (Question Generation) type: meteor_question_generation value: 23.69 - name: BERTScore (Question Generation) type: bertscore_question_generation value: 76.82 - name: MoverScore (Question Generation) type: moverscore_question_generation value: 57.24 - name: QAAlignedF1Score-BERTScore (Question & Answer Generation (with Gold Answer)) type: qa_aligned_f1_score_bertscore_question_answer_generation_with_gold_answer value: 78.4 - name: QAAlignedRecall-BERTScore (Question & Answer Generation (with Gold Answer)) type: qa_aligned_recall_bertscore_question_answer_generation_with_gold_answer value: 81.92 - name: QAAlignedPrecision-BERTScore (Question & Answer Generation (with Gold Answer)) type: qa_aligned_precision_bertscore_question_answer_generation_with_gold_answer value: 75.27 - name: QAAlignedF1Score-MoverScore (Question & Answer Generation (with Gold Answer)) type: qa_aligned_f1_score_moverscore_question_answer_generation_with_gold_answer value: 53.55 - name: QAAlignedRecall-MoverScore (Question & Answer Generation (with Gold Answer)) type: qa_aligned_recall_moverscore_question_answer_generation_with_gold_answer value: 55.82 - name: QAAlignedPrecision-MoverScore (Question & Answer Generation (with Gold Answer)) type: qa_aligned_precision_moverscore_question_answer_generation_with_gold_answer value: 51.56 - name: BLEU4 (Answer Extraction) type: bleu4_answer_extraction value: 82.63 - name: ROUGE-L (Answer Extraction) type: rouge_l_answer_extraction value: 95.72 - name: METEOR (Answer Extraction) type: meteor_answer_extraction value: 71.18 - name: BERTScore (Answer Extraction) type: bertscore_answer_extraction value: 99.76 - name: MoverScore (Answer Extraction) type: moverscore_answer_extraction value: 98.8 - name: AnswerF1Score (Answer Extraction) type: answer_f1_score__answer_extraction value: 95.15 - name: AnswerExactMatch (Answer Extraction) type: answer_exact_match_answer_extraction value: 95.07 --- # Model Card of `lmqg/mt5-base-zhquad-qg-ae` This model is fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) for question generation and answer extraction jointly on the [lmqg/qg_zhquad](https://huggingface.co/datasets/lmqg/qg_zhquad) (dataset_name: default) via [`lmqg`](https://github.com/asahi417/lm-question-generation). ### Overview - **Language model:** [google/mt5-base](https://huggingface.co/google/mt5-base) - **Language:** zh - **Training data:** [lmqg/qg_zhquad](https://huggingface.co/datasets/lmqg/qg_zhquad) (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="zh", model="lmqg/mt5-base-zhquad-qg-ae") # model prediction question_answer_pairs = model.generate_qa("南安普敦的警察服务由汉普郡警察提供。南安普敦行动的主要基地是一座新的八层专用建筑，造价3000万英镑。该建筑位于南路，2011年启用，靠近南安普敦中央火车站。此前，南安普顿市中心的行动位于市民中心西翼，但由于设施老化，加上计划在旧警察局和地方法院建造一座新博物馆，因此必须搬迁。在Portswood、Banister Park、Hille和Shirley还有其他警察局，在南安普顿中央火车站还有一个英国交通警察局。") ``` - With `transformers` ```python from transformers import pipeline pipe = pipeline("text2text-generation", "lmqg/mt5-base-zhquad-qg-ae") # answer extraction answer = pipe("generate question: 南安普敦的警察服务由汉普郡警察提供。南安普敦行动的主要基地是一座新的八层专用建筑，造价3000万英镑。该建筑位于南路，2011年启用，靠近 南安普敦中央 火车站。此前，南安普顿市中心的行动位于市民中心西翼，但由于设施老化，加上计划在旧警察局和地方法院建造一座新博物馆，因此必须搬迁。在Portswood、Banister Park、Hille和Shirley还有其他警察局，在南安普顿中央火车站还有一个英国交通警察局。") # question generation question = pipe("extract answers: 南安普敦的警察服务由汉普郡警察提供。 南安普敦行动的主要基地是一座新的八层专用建筑，造价3000万英镑。 该建筑位于南路，2011年启用，靠近 南安普敦中央 火车站。 此前，南安普顿市中心的行动位于市民中心西翼，但由于设施老化，加上计划在旧警察局和地方法院建造一座新博物馆，因此必须搬迁。 在Portswood、Banister Park、Hille和Shirley还有其他警察局，在南安普顿中央火车站还有一个英国交通警察局。") ``` ## Evaluation - ***Metric (Question Generation)***: [raw metric file](https://huggingface.co/lmqg/mt5-base-zhquad-qg-ae/raw/main/eval/metric.first.sentence.paragraph_answer.question.lmqg_qg_zhquad.default.json) | | Score | Type | Dataset | |:-----------|--------:|:--------|:-----------------------------------------------------------------| | BERTScore | 76.82 | default | [lmqg/qg_zhquad](https://huggingface.co/datasets/lmqg/qg_zhquad) | | Bleu_1 | 36.9 | default | [lmqg/qg_zhquad](https://huggingface.co/datasets/lmqg/qg_zhquad) | | Bleu_2 | 25.74 | default | [lmqg/qg_zhquad](https://huggingface.co/datasets/lmqg/qg_zhquad) | | Bleu_3 | 19.13 | default | [lmqg/qg_zhquad](https://huggingface.co/datasets/lmqg/qg_zhquad) | | Bleu_4 | 14.63 | default | [lmqg/qg_zhquad](https://huggingface.co/datasets/lmqg/qg_zhquad) | | METEOR | 23.69 | default | [lmqg/qg_zhquad](https://huggingface.co/datasets/lmqg/qg_zhquad) | | MoverScore | 57.24 | default | [lmqg/qg_zhquad](https://huggingface.co/datasets/lmqg/qg_zhquad) | | ROUGE_L | 34.07 | default | [lmqg/qg_zhquad](https://huggingface.co/datasets/lmqg/qg_zhquad) | - ***Metric (Question & Answer Generation)***: [raw metric file](https://huggingface.co/lmqg/mt5-base-zhquad-qg-ae/raw/main/eval/metric.first.answer.paragraph.questions_answers.lmqg_qg_zhquad.default.json) | | Score | Type | Dataset | |:--------------------------------|--------:|:--------|:-----------------------------------------------------------------| | QAAlignedF1Score (BERTScore) | 78.4 | default | [lmqg/qg_zhquad](https://huggingface.co/datasets/lmqg/qg_zhquad) | | QAAlignedF1Score (MoverScore) | 53.55 | default | [lmqg/qg_zhquad](https://huggingface.co/datasets/lmqg/qg_zhquad) | | QAAlignedPrecision (BERTScore) | 75.27 | default | [lmqg/qg_zhquad](https://huggingface.co/datasets/lmqg/qg_zhquad) | | QAAlignedPrecision (MoverScore) | 51.56 | default | [lmqg/qg_zhquad](https://huggingface.co/datasets/lmqg/qg_zhquad) | | QAAlignedRecall (BERTScore) | 81.92 | default | [lmqg/qg_zhquad](https://huggingface.co/datasets/lmqg/qg_zhquad) | | QAAlignedRecall (MoverScore) | 55.82 | default | [lmqg/qg_zhquad](https://huggingface.co/datasets/lmqg/qg_zhquad) | - ***Metric (Answer Extraction)***: [raw metric file](https://huggingface.co/lmqg/mt5-base-zhquad-qg-ae/raw/main/eval/metric.first.answer.paragraph_sentence.answer.lmqg_qg_zhquad.default.json) | | Score | Type | Dataset | |:-----------------|--------:|:--------|:-----------------------------------------------------------------| | AnswerExactMatch | 95.07 | default | [lmqg/qg_zhquad](https://huggingface.co/datasets/lmqg/qg_zhquad) | | AnswerF1Score | 95.15 | default | [lmqg/qg_zhquad](https://huggingface.co/datasets/lmqg/qg_zhquad) | | BERTScore | 99.76 | default | [lmqg/qg_zhquad](https://huggingface.co/datasets/lmqg/qg_zhquad) | | Bleu_1 | 92.37 | default | [lmqg/qg_zhquad](https://huggingface.co/datasets/lmqg/qg_zhquad) | | Bleu_2 | 89.37 | default | [lmqg/qg_zhquad](https://huggingface.co/datasets/lmqg/qg_zhquad) | | Bleu_3 | 86.14 | default | [lmqg/qg_zhquad](https://huggingface.co/datasets/lmqg/qg_zhquad) | | Bleu_4 | 82.63 | default | [lmqg/qg_zhquad](https://huggingface.co/datasets/lmqg/qg_zhquad) | | METEOR | 71.18 | default | [lmqg/qg_zhquad](https://huggingface.co/datasets/lmqg/qg_zhquad) | | MoverScore | 98.8 | default | [lmqg/qg_zhquad](https://huggingface.co/datasets/lmqg/qg_zhquad) | | ROUGE_L | 95.72 | default | [lmqg/qg_zhquad](https://huggingface.co/datasets/lmqg/qg_zhquad) | ## Training hyperparameters The following hyperparameters were used during fine-tuning: - dataset_path: lmqg/qg_zhquad - dataset_name: default - input_types: ['paragraph_answer', 'paragraph_sentence'] - output_types: ['question', 'answer'] - prefix_types: ['qg', 'ae'] - model: google/mt5-base - max_length: 512 - max_length_output: 32 - epoch: 5 - batch: 32 - lr: 0.0005 - 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/mt5-base-zhquad-qg-ae/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", } ```