--- license: cc-by-4.0 metrics: - bleu4 - meteor - rouge-l - bertscore - moverscore language: fr datasets: - lmqg/qg_frquad pipeline_tag: text2text-generation tags: - question generation widget: - text: "Créateur » (Maker), lui aussi au singulier, « le Suprême Berger » (The Great Shepherd) ; de l'autre, des réminiscences de la théologie de l'Antiquité : le tonnerre, voix de Jupiter, « Et souvent ta voix gronde en un tonnerre terrifiant », etc." example_title: "Question Generation Example 1" - text: "Ce black dog peut être lié à des évènements traumatisants issus du monde extérieur, tels que son renvoi de l'Amirauté après la catastrophe des Dardanelles, lors de la Grande Guerre de 14-18, ou son rejet par l'électorat en juillet 1945." example_title: "Question Generation Example 2" - text: "contre Normie Smith et 15 000 dollars le 28 novembre 1938." example_title: "Question Generation Example 3" model-index: - name: lmqg/mt5-base-frquad-qg results: - task: name: Text2text Generation type: text2text-generation dataset: name: lmqg/qg_frquad type: default args: default metrics: - name: BLEU4 (Question Generation) type: bleu4_question_generation value: 6.14 - name: ROUGE-L (Question Generation) type: rouge_l_question_generation value: 25.88 - name: METEOR (Question Generation) type: meteor_question_generation value: 15.55 - name: BERTScore (Question Generation) type: bertscore_question_generation value: 77.81 - name: MoverScore (Question Generation) type: moverscore_question_generation value: 54.58 - name: QAAlignedF1Score-BERTScore (Question & Answer Generation (with Gold Answer)) [Gold Answer] type: qa_aligned_f1_score_bertscore_question_answer_generation_with_gold_answer_gold_answer value: 86.41 - name: QAAlignedRecall-BERTScore (Question & Answer Generation (with Gold Answer)) [Gold Answer] type: qa_aligned_recall_bertscore_question_answer_generation_with_gold_answer_gold_answer value: 86.4 - name: QAAlignedPrecision-BERTScore (Question & Answer Generation (with Gold Answer)) [Gold Answer] type: qa_aligned_precision_bertscore_question_answer_generation_with_gold_answer_gold_answer value: 86.42 - name: QAAlignedF1Score-MoverScore (Question & Answer Generation (with Gold Answer)) [Gold Answer] type: qa_aligned_f1_score_moverscore_question_answer_generation_with_gold_answer_gold_answer value: 60.19 - name: QAAlignedRecall-MoverScore (Question & Answer Generation (with Gold Answer)) [Gold Answer] type: qa_aligned_recall_moverscore_question_answer_generation_with_gold_answer_gold_answer value: 60.18 - name: QAAlignedPrecision-MoverScore (Question & Answer Generation (with Gold Answer)) [Gold Answer] type: qa_aligned_precision_moverscore_question_answer_generation_with_gold_answer_gold_answer value: 60.19 - name: QAAlignedF1Score-BERTScore (Question & Answer Generation) [Gold Answer] type: qa_aligned_f1_score_bertscore_question_answer_generation_gold_answer value: 68.59 - name: QAAlignedRecall-BERTScore (Question & Answer Generation) [Gold Answer] type: qa_aligned_recall_bertscore_question_answer_generation_gold_answer value: 69.69 - name: QAAlignedPrecision-BERTScore (Question & Answer Generation) [Gold Answer] type: qa_aligned_precision_bertscore_question_answer_generation_gold_answer value: 67.59 - name: QAAlignedF1Score-MoverScore (Question & Answer Generation) [Gold Answer] type: qa_aligned_f1_score_moverscore_question_answer_generation_gold_answer value: 47.87 - name: QAAlignedRecall-MoverScore (Question & Answer Generation) [Gold Answer] type: qa_aligned_recall_moverscore_question_answer_generation_gold_answer value: 48.36 - name: QAAlignedPrecision-MoverScore (Question & Answer Generation) [Gold Answer] type: qa_aligned_precision_moverscore_question_answer_generation_gold_answer value: 47.42 --- # Model Card of `lmqg/mt5-base-frquad-qg` This model is fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) for question generation task on the [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) (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:** fr - **Training data:** [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) (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="fr", model="lmqg/mt5-base-frquad-qg") # model prediction questions = model.generate_q(list_context="Créateur » (Maker), lui aussi au singulier, « le Suprême Berger » (The Great Shepherd) ; de l'autre, des réminiscences de la théologie de l'Antiquité : le tonnerre, voix de Jupiter, « Et souvent ta voix gronde en un tonnerre terrifiant », etc.", list_answer="le Suprême Berger") ``` - With `transformers` ```python from transformers import pipeline pipe = pipeline("text2text-generation", "lmqg/mt5-base-frquad-qg") output = pipe("Créateur » (Maker), lui aussi au singulier, « le Suprême Berger » (The Great Shepherd) ; de l'autre, des réminiscences de la théologie de l'Antiquité : le tonnerre, voix de Jupiter, « Et souvent ta voix gronde en un tonnerre terrifiant », etc.") ``` ## Evaluation - ***Metric (Question Generation)***: [raw metric file](https://huggingface.co/lmqg/mt5-base-frquad-qg/raw/main/eval/metric.first.sentence.paragraph_answer.question.lmqg_qg_frquad.default.json) | | Score | Type | Dataset | |:-----------|--------:|:--------|:-----------------------------------------------------------------| | BERTScore | 77.81 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) | | Bleu_1 | 25.06 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) | | Bleu_2 | 13.73 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) | | Bleu_3 | 8.93 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) | | Bleu_4 | 6.14 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) | | METEOR | 15.55 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) | | MoverScore | 54.58 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) | | ROUGE_L | 25.88 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) | - ***Metric (Question & Answer Generation, Reference Answer)***: Each question is generated from *the gold answer*. [raw metric file](https://huggingface.co/lmqg/mt5-base-frquad-qg/raw/main/eval/metric.first.answer.paragraph.questions_answers.lmqg_qg_frquad.default.json) | | Score | Type | Dataset | |:--------------------------------|--------:|:--------|:-----------------------------------------------------------------| | QAAlignedF1Score (BERTScore) | 86.41 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) | | QAAlignedF1Score (MoverScore) | 60.19 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) | | QAAlignedPrecision (BERTScore) | 86.42 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) | | QAAlignedPrecision (MoverScore) | 60.19 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) | | QAAlignedRecall (BERTScore) | 86.4 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) | | QAAlignedRecall (MoverScore) | 60.18 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) | - ***Metric (Question & Answer Generation, Pipeline Approach)***: Each question is generated on the answer generated by [`lmqg/mt5-base-frquad-ae`](https://huggingface.co/lmqg/mt5-base-frquad-ae). [raw metric file](https://huggingface.co/lmqg/mt5-base-frquad-qg/raw/main/eval_pipeline/metric.first.answer.paragraph.questions_answers.lmqg_qg_frquad.default.lmqg_mt5-base-frquad-ae.json) | | Score | Type | Dataset | |:--------------------------------|--------:|:--------|:-----------------------------------------------------------------| | QAAlignedF1Score (BERTScore) | 68.59 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) | | QAAlignedF1Score (MoverScore) | 47.87 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) | | QAAlignedPrecision (BERTScore) | 67.59 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) | | QAAlignedPrecision (MoverScore) | 47.42 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) | | QAAlignedRecall (BERTScore) | 69.69 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) | | QAAlignedRecall (MoverScore) | 48.36 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) | ## Training hyperparameters The following hyperparameters were used during fine-tuning: - dataset_path: lmqg/qg_frquad - dataset_name: default - input_types: ['paragraph_answer'] - output_types: ['question'] - prefix_types: None - model: google/mt5-base - max_length: 512 - max_length_output: 32 - epoch: 24 - batch: 4 - lr: 0.0001 - fp16: False - random_seed: 1 - gradient_accumulation_steps: 16 - label_smoothing: 0.15 The full configuration can be found at [fine-tuning config file](https://huggingface.co/lmqg/mt5-base-frquad-qg/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", } ```