--- license: cc-by-4.0 metrics: - bleu4 - meteor - rouge-l - bertscore - moverscore language: it datasets: - lmqg/qg_itquad pipeline_tag: text2text-generation tags: - question generation - answer extraction widget: - text: "generate question: Dopo il 1971 , l' OPEC ha tardato ad adeguare i prezzi per riflettere tale deprezzamento." example_title: "Question Generation Example 1" - text: "generate question: L' individuazione del petrolio e lo sviluppo di nuovi giacimenti richiedeva in genere da cinque a dieci anni prima di una produzione significativa." example_title: "Question Generation Example 2" - text: "generate question: il Giappone è stato il paese più dipendente dal petrolio arabo." example_title: "Question Generation Example 3" - text: "extract answers: Il 6 ottobre 1973 , la Siria e l' Egitto, con il sostegno di altre nazioni arabe, lanciarono un attacco a sorpresa su Israele, su Yom Kippur. Questo rinnovo delle ostilità nel conflitto arabo-israeliano ha liberato la pressione economica sottostante sui prezzi del petrolio. All' epoca, l' Iran era il secondo esportatore mondiale di petrolio e un vicino alleato degli Stati Uniti. Settimane più tardi, lo scià d' Iran ha detto in un' intervista: Naturalmente[il prezzo del petrolio] sta andando a salire Certamente! E come! Avete[Paesi occidentali] aumentato il prezzo del grano che ci vendete del 300 per cento, e lo stesso per zucchero e cemento." example_title: "Answer Extraction Example 1" - text: "extract answers: Furono introdotti autocarri compatti, come la Toyota Hilux e il Datsun Truck, seguiti dal camion Mazda (venduto come il Ford Courier), e l' Isuzu costruito Chevrolet LUV. Mitsubishi rebranded il suo Forte come Dodge D-50 pochi anni dopo la crisi petrolifera. Mazda, Mitsubishi e Isuzu avevano partnership congiunte rispettivamente con Ford, Chrysler e GM. In seguito i produttori americani introdussero le loro sostituzioni nazionali (Ford Ranger, Dodge Dakota e la Chevrolet S10/GMC S-15), ponendo fine alla loro politica di importazione vincolata." example_title: "Answer Extraction Example 2" model-index: - name: lmqg/mbart-large-cc25-itquad-qg-ae results: - task: name: Text2text Generation type: text2text-generation dataset: name: lmqg/qg_itquad type: default args: default metrics: - name: BLEU4 (Question Generation) type: bleu4_question_generation value: 7.06 - name: ROUGE-L (Question Generation) type: rouge_l_question_generation value: 20.15 - name: METEOR (Question Generation) type: meteor_question_generation value: 16.86 - name: BERTScore (Question Generation) type: bertscore_question_generation value: 79.29 - name: MoverScore (Question Generation) type: moverscore_question_generation value: 55.92 - name: QAAlignedF1Score-BERTScore (Question & Answer Generation (with Gold Answer)) type: qa_aligned_f1_score_bertscore_question_answer_generation_with_gold_answer value: 82.65 - name: QAAlignedRecall-BERTScore (Question & Answer Generation (with Gold Answer)) type: qa_aligned_recall_bertscore_question_answer_generation_with_gold_answer value: 84.34 - name: QAAlignedPrecision-BERTScore (Question & Answer Generation (with Gold Answer)) type: qa_aligned_precision_bertscore_question_answer_generation_with_gold_answer value: 81.06 - name: QAAlignedF1Score-MoverScore (Question & Answer Generation (with Gold Answer)) type: qa_aligned_f1_score_moverscore_question_answer_generation_with_gold_answer value: 56.14 - name: QAAlignedRecall-MoverScore (Question & Answer Generation (with Gold Answer)) type: qa_aligned_recall_moverscore_question_answer_generation_with_gold_answer value: 57.13 - name: QAAlignedPrecision-MoverScore (Question & Answer Generation (with Gold Answer)) type: qa_aligned_precision_moverscore_question_answer_generation_with_gold_answer value: 55.22 - name: BLEU4 (Answer Extraction) type: bleu4_answer_extraction value: 20.21 - name: ROUGE-L (Answer Extraction) type: rouge_l_answer_extraction value: 46.51 - name: METEOR (Answer Extraction) type: meteor_answer_extraction value: 44.48 - name: BERTScore (Answer Extraction) type: bertscore_answer_extraction value: 90.63 - name: MoverScore (Answer Extraction) type: moverscore_answer_extraction value: 83.05 - name: AnswerF1Score (Answer Extraction) type: answer_f1_score__answer_extraction value: 76.59 - name: AnswerExactMatch (Answer Extraction) type: answer_exact_match_answer_extraction value: 63.88 --- # Model Card of `lmqg/mbart-large-cc25-itquad-qg-ae` This model is fine-tuned version of [facebook/mbart-large-cc25](https://huggingface.co/facebook/mbart-large-cc25) for question generation and answer extraction jointly on the [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) (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:** it - **Training data:** [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) (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="it", model="lmqg/mbart-large-cc25-itquad-qg-ae") # model prediction question_answer_pairs = model.generate_qa("Dopo il 1971 , l' OPEC ha tardato ad adeguare i prezzi per riflettere tale deprezzamento.") ``` - With `transformers` ```python from transformers import pipeline pipe = pipeline("text2text-generation", "lmqg/mbart-large-cc25-itquad-qg-ae") # answer extraction answer = pipe("generate question: Dopo il 1971 , l' OPEC ha tardato ad adeguare i prezzi per riflettere tale deprezzamento.") # question generation question = pipe("extract answers: Il 6 ottobre 1973 , la Siria e l' Egitto, con il sostegno di altre nazioni arabe, lanciarono un attacco a sorpresa su Israele, su Yom Kippur. Questo rinnovo delle ostilità nel conflitto arabo-israeliano ha liberato la pressione economica sottostante sui prezzi del petrolio. All' epoca, l' Iran era il secondo esportatore mondiale di petrolio e un vicino alleato degli Stati Uniti. Settimane più tardi, lo scià d' Iran ha detto in un' intervista: Naturalmente[il prezzo del petrolio] sta andando a salire Certamente! E come! Avete[Paesi occidentali] aumentato il prezzo del grano che ci vendete del 300 per cento, e lo stesso per zucchero e cemento.") ``` ## Evaluation - ***Metric (Question Generation)***: [raw metric file](https://huggingface.co/lmqg/mbart-large-cc25-itquad-qg-ae/raw/main/eval/metric.first.sentence.paragraph_answer.question.lmqg_qg_itquad.default.json) | | Score | Type | Dataset | |:-----------|--------:|:--------|:-----------------------------------------------------------------| | BERTScore | 79.29 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) | | Bleu_1 | 22.03 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) | | Bleu_2 | 14.31 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) | | Bleu_3 | 9.9 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) | | Bleu_4 | 7.06 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) | | METEOR | 16.86 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) | | MoverScore | 55.92 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) | | ROUGE_L | 20.15 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) | - ***Metric (Question & Answer Generation)***: [raw metric file](https://huggingface.co/lmqg/mbart-large-cc25-itquad-qg-ae/raw/main/eval/metric.first.answer.paragraph.questions_answers.lmqg_qg_itquad.default.json) | | Score | Type | Dataset | |:--------------------------------|--------:|:--------|:-----------------------------------------------------------------| | QAAlignedF1Score (BERTScore) | 82.65 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) | | QAAlignedF1Score (MoverScore) | 56.14 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) | | QAAlignedPrecision (BERTScore) | 81.06 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) | | QAAlignedPrecision (MoverScore) | 55.22 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) | | QAAlignedRecall (BERTScore) | 84.34 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) | | QAAlignedRecall (MoverScore) | 57.13 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) | - ***Metric (Answer Extraction)***: [raw metric file](https://huggingface.co/lmqg/mbart-large-cc25-itquad-qg-ae/raw/main/eval/metric.first.answer.paragraph_sentence.answer.lmqg_qg_itquad.default.json) | | Score | Type | Dataset | |:-----------------|--------:|:--------|:-----------------------------------------------------------------| | AnswerExactMatch | 63.88 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) | | AnswerF1Score | 76.59 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) | | BERTScore | 90.63 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) | | Bleu_1 | 33.66 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) | | Bleu_2 | 27.96 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) | | Bleu_3 | 23.79 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) | | Bleu_4 | 20.21 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) | | METEOR | 44.48 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) | | MoverScore | 83.05 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) | | ROUGE_L | 46.51 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) | ## Training hyperparameters The following hyperparameters were used during fine-tuning: - dataset_path: lmqg/qg_itquad - dataset_name: default - input_types: ['paragraph_answer', 'paragraph_sentence'] - output_types: ['question', 'answer'] - prefix_types: ['qg', 'ae'] - model: facebook/mbart-large-cc25 - max_length: 512 - max_length_output: 32 - epoch: 8 - batch: 2 - lr: 0.0001 - fp16: False - random_seed: 1 - gradient_accumulation_steps: 32 - label_smoothing: 0.15 The full configuration can be found at [fine-tuning config file](https://huggingface.co/lmqg/mbart-large-cc25-itquad-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", } ```