--- license: cc-by-4.0 metrics: - bleu4 - meteor - rouge-l - bertscore - moverscore language: de datasets: - lmqg/qg_dequad pipeline_tag: text2text-generation tags: - question generation widget: - text: "Empfangs- und Sendeantenne sollen in ihrer Polarisation übereinstimmen, andernfalls wird die Signalübertragung stark gedämpft. " example_title: "Question Generation Example 1" - text: "das erste weltweit errichtete Hermann Brehmer 1855 im niederschlesischen ''Görbersdorf'' (heute Sokołowsko, Polen)." example_title: "Question Generation Example 2" - text: "Er muss Zyperngrieche sein und wird direkt für fünf Jahre gewählt (Art. 43 Abs. 1 der Verfassung) und verfügt über weitreichende Exekutivkompetenzen." example_title: "Question Generation Example 3" model-index: - name: lmqg/mbart-large-cc25-dequad-qg results: - task: name: Text2text Generation type: text2text-generation dataset: name: lmqg/qg_dequad type: default args: default metrics: - name: BLEU4 (Question Generation) type: bleu4_question_generation value: 0.75 - name: ROUGE-L (Question Generation) type: rouge_l_question_generation value: 11.19 - name: METEOR (Question Generation) type: meteor_question_generation value: 13.71 - name: BERTScore (Question Generation) type: bertscore_question_generation value: 80.77 - name: MoverScore (Question Generation) type: moverscore_question_generation value: 55.88 - 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: 90.66 - 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: 90.69 - 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: 90.64 - 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: 65.36 - 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: 65.36 - 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: 65.37 - name: QAAlignedF1Score-BERTScore (Question & Answer Generation) [Gold Answer] type: qa_aligned_f1_score_bertscore_question_answer_generation_gold_answer value: 0.0 - name: QAAlignedRecall-BERTScore (Question & Answer Generation) [Gold Answer] type: qa_aligned_recall_bertscore_question_answer_generation_gold_answer value: 0.0 - name: QAAlignedPrecision-BERTScore (Question & Answer Generation) [Gold Answer] type: qa_aligned_precision_bertscore_question_answer_generation_gold_answer value: 0.0 - name: QAAlignedF1Score-MoverScore (Question & Answer Generation) [Gold Answer] type: qa_aligned_f1_score_moverscore_question_answer_generation_gold_answer value: 0.0 - name: QAAlignedRecall-MoverScore (Question & Answer Generation) [Gold Answer] type: qa_aligned_recall_moverscore_question_answer_generation_gold_answer value: 0.0 - name: QAAlignedPrecision-MoverScore (Question & Answer Generation) [Gold Answer] type: qa_aligned_precision_moverscore_question_answer_generation_gold_answer value: 0.0 --- # Model Card of `lmqg/mbart-large-cc25-dequad-qg` This model is fine-tuned version of [facebook/mbart-large-cc25](https://huggingface.co/facebook/mbart-large-cc25) for question generation task on the [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) (dataset_name: default) via [`lmqg`](https://github.com/asahi417/lm-question-generation). ### Overview - **Language model:** [facebook/mbart-large-cc25](https://huggingface.co/facebook/mbart-large-cc25) - **Language:** de - **Training data:** [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) (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="de", model="lmqg/mbart-large-cc25-dequad-qg") # model prediction questions = model.generate_q(list_context="das erste weltweit errichtete Hermann Brehmer 1855 im niederschlesischen ''Görbersdorf'' (heute Sokołowsko, Polen).", list_answer="1855") ``` - With `transformers` ```python from transformers import pipeline pipe = pipeline("text2text-generation", "lmqg/mbart-large-cc25-dequad-qg") output = pipe("Empfangs- und Sendeantenne sollen in ihrer Polarisation übereinstimmen, andernfalls wird die Signalübertragung stark gedämpft. ") ``` ## Evaluation - ***Metric (Question Generation)***: [raw metric file](https://huggingface.co/lmqg/mbart-large-cc25-dequad-qg/raw/main/eval/metric.first.sentence.paragraph_answer.question.lmqg_qg_dequad.default.json) | | Score | Type | Dataset | |:-----------|--------:|:--------|:-----------------------------------------------------------------| | BERTScore | 80.77 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) | | Bleu_1 | 10.96 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) | | Bleu_2 | 4.48 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) | | Bleu_3 | 1.91 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) | | Bleu_4 | 0.75 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) | | METEOR | 13.71 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) | | MoverScore | 55.88 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) | | ROUGE_L | 11.19 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) | - ***Metric (Question & Answer Generation, Reference Answer)***: Each question is generated from *the gold answer*. [raw metric file](https://huggingface.co/lmqg/mbart-large-cc25-dequad-qg/raw/main/eval/metric.first.answer.paragraph.questions_answers.lmqg_qg_dequad.default.json) | | Score | Type | Dataset | |:--------------------------------|--------:|:--------|:-----------------------------------------------------------------| | QAAlignedF1Score (BERTScore) | 90.66 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) | | QAAlignedF1Score (MoverScore) | 65.36 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) | | QAAlignedPrecision (BERTScore) | 90.64 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) | | QAAlignedPrecision (MoverScore) | 65.37 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) | | QAAlignedRecall (BERTScore) | 90.69 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) | | QAAlignedRecall (MoverScore) | 65.36 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) | - ***Metric (Question & Answer Generation, Pipeline Approach)***: Each question is generated on the answer generated by [`lmqg/mbart-large-cc25-dequad-ae`](https://huggingface.co/lmqg/mbart-large-cc25-dequad-ae). [raw metric file](https://huggingface.co/lmqg/mbart-large-cc25-dequad-qg/raw/main/eval_pipeline/metric.first.answer.paragraph.questions_answers.lmqg_qg_dequad.default.lmqg_mbart-large-cc25-dequad-ae.json) | | Score | Type | Dataset | |:--------------------------------|--------:|:--------|:-----------------------------------------------------------------| | QAAlignedF1Score (BERTScore) | 0 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) | | QAAlignedF1Score (MoverScore) | 0 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) | | QAAlignedPrecision (BERTScore) | 0 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) | | QAAlignedPrecision (MoverScore) | 0 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) | | QAAlignedRecall (BERTScore) | 0 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) | | QAAlignedRecall (MoverScore) | 0 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) | ## Training hyperparameters The following hyperparameters were used during fine-tuning: - dataset_path: lmqg/qg_dequad - dataset_name: default - input_types: ['paragraph_answer'] - output_types: ['question'] - prefix_types: None - model: facebook/mbart-large-cc25 - max_length: 512 - max_length_output: 32 - epoch: 11 - 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/mbart-large-cc25-dequad-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", } ```