commit files to HF hub

README.md

@@ -0,0 +1,211 @@
+
+---
+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<hl> 南安普敦中央 <hl>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<hl> 1960—61 <hl>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。 <hl> 该建筑位于南路，2011年启用，靠近 南安普敦中央 火车站。 <hl> 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-small-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: 13.98
+    - name: ROUGE-L (Question Generation)
+      type: rouge_l_question_generation
+      value: 33.17
+    - name: METEOR (Question Generation)
+      type: meteor_question_generation
+      value: 22.88
+    - name: BERTScore (Question Generation)
+      type: bertscore_question_generation
+      value: 76.64
+    - name: MoverScore (Question Generation)
+      type: moverscore_question_generation
+      value: 57.03
+    - name: QAAlignedF1Score-BERTScore (Question & Answer Generation (with Gold Answer))
+      type: qa_aligned_f1_score_bertscore_question_answer_generation_with_gold_answer
+      value: 78.55
+    - name: QAAlignedRecall-BERTScore (Question & Answer Generation (with Gold Answer))
+      type: qa_aligned_recall_bertscore_question_answer_generation_with_gold_answer
+      value: 82.09
+    - name: QAAlignedPrecision-BERTScore (Question & Answer Generation (with Gold Answer))
+      type: qa_aligned_precision_bertscore_question_answer_generation_with_gold_answer
+      value: 75.41
+    - name: QAAlignedF1Score-MoverScore (Question & Answer Generation (with Gold Answer))
+      type: qa_aligned_f1_score_moverscore_question_answer_generation_with_gold_answer
+      value: 53.47
+    - name: QAAlignedRecall-MoverScore (Question & Answer Generation (with Gold Answer))
+      type: qa_aligned_recall_moverscore_question_answer_generation_with_gold_answer
+      value: 55.73
+    - name: QAAlignedPrecision-MoverScore (Question & Answer Generation (with Gold Answer))
+      type: qa_aligned_precision_moverscore_question_answer_generation_with_gold_answer
+      value: 51.5
+    - name: BLEU4 (Answer Extraction)
+      type: bleu4_answer_extraction
+      value: 81.9
+    - name: ROUGE-L (Answer Extraction)
+      type: rouge_l_answer_extraction
+      value: 95.05
+    - name: METEOR (Answer Extraction)
+      type: meteor_answer_extraction
+      value: 69.99
+    - name: BERTScore (Answer Extraction)
+      type: bertscore_answer_extraction
+      value: 99.69
+    - name: MoverScore (Answer Extraction)
+      type: moverscore_answer_extraction
+      value: 98.34
+    - name: AnswerF1Score (Answer Extraction)
+      type: answer_f1_score__answer_extraction
+      value: 93.58
+    - name: AnswerExactMatch (Answer Extraction)
+      type: answer_exact_match_answer_extraction
+      value: 93.5
+---
+
+# Model Card of `lmqg/mt5-small-zhquad-qg-ae`
+This model is fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) 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-small](https://huggingface.co/google/mt5-small)   
+- **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-small-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-small-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<hl> 南安普敦中央 <hl>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。 <hl> 该建筑位于南路，2011年启用，靠近 南安普敦中央 火车站。 <hl> 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-small-zhquad-qg-ae/raw/main/eval/metric.first.sentence.paragraph_answer.question.lmqg_qg_zhquad.default.json) 
+
+|            |   Score | Type    | Dataset                                                          |
+|:-----------|--------:|:--------|:-----------------------------------------------------------------|
+| BERTScore  |   76.64 | default | [lmqg/qg_zhquad](https://huggingface.co/datasets/lmqg/qg_zhquad) |
+| Bleu_1     |   35.24 | default | [lmqg/qg_zhquad](https://huggingface.co/datasets/lmqg/qg_zhquad) |
+| Bleu_2     |   24.56 | default | [lmqg/qg_zhquad](https://huggingface.co/datasets/lmqg/qg_zhquad) |
+| Bleu_3     |   18.21 | default | [lmqg/qg_zhquad](https://huggingface.co/datasets/lmqg/qg_zhquad) |
+| Bleu_4     |   13.98 | default | [lmqg/qg_zhquad](https://huggingface.co/datasets/lmqg/qg_zhquad) |
+| METEOR     |   22.88 | default | [lmqg/qg_zhquad](https://huggingface.co/datasets/lmqg/qg_zhquad) |
+| MoverScore |   57.03 | default | [lmqg/qg_zhquad](https://huggingface.co/datasets/lmqg/qg_zhquad) |
+| ROUGE_L    |   33.17 | default | [lmqg/qg_zhquad](https://huggingface.co/datasets/lmqg/qg_zhquad) |
+
+
+- ***Metric (Question & Answer Generation)***:  [raw metric file](https://huggingface.co/lmqg/mt5-small-zhquad-qg-ae/raw/main/eval/metric.first.answer.paragraph.questions_answers.lmqg_qg_zhquad.default.json)
+
+|                                 |   Score | Type    | Dataset                                                          |
+|:--------------------------------|--------:|:--------|:-----------------------------------------------------------------|
+| QAAlignedF1Score (BERTScore)    |   78.55 | default | [lmqg/qg_zhquad](https://huggingface.co/datasets/lmqg/qg_zhquad) |
+| QAAlignedF1Score (MoverScore)   |   53.47 | default | [lmqg/qg_zhquad](https://huggingface.co/datasets/lmqg/qg_zhquad) |
+| QAAlignedPrecision (BERTScore)  |   75.41 | default | [lmqg/qg_zhquad](https://huggingface.co/datasets/lmqg/qg_zhquad) |
+| QAAlignedPrecision (MoverScore) |   51.5  | default | [lmqg/qg_zhquad](https://huggingface.co/datasets/lmqg/qg_zhquad) |
+| QAAlignedRecall (BERTScore)     |   82.09 | default | [lmqg/qg_zhquad](https://huggingface.co/datasets/lmqg/qg_zhquad) |
+| QAAlignedRecall (MoverScore)    |   55.73 | default | [lmqg/qg_zhquad](https://huggingface.co/datasets/lmqg/qg_zhquad) |
+
+
+- ***Metric (Answer Extraction)***: [raw metric file](https://huggingface.co/lmqg/mt5-small-zhquad-qg-ae/raw/main/eval/metric.first.answer.paragraph_sentence.answer.lmqg_qg_zhquad.default.json)
+
+|                  |   Score | Type    | Dataset                                                          |
+|:-----------------|--------:|:--------|:-----------------------------------------------------------------|
+| AnswerExactMatch |   93.5  | default | [lmqg/qg_zhquad](https://huggingface.co/datasets/lmqg/qg_zhquad) |
+| AnswerF1Score    |   93.58 | default | [lmqg/qg_zhquad](https://huggingface.co/datasets/lmqg/qg_zhquad) |
+| BERTScore        |   99.69 | default | [lmqg/qg_zhquad](https://huggingface.co/datasets/lmqg/qg_zhquad) |
+| Bleu_1           |   92    | default | [lmqg/qg_zhquad](https://huggingface.co/datasets/lmqg/qg_zhquad) |
+| Bleu_2           |   88.87 | default | [lmqg/qg_zhquad](https://huggingface.co/datasets/lmqg/qg_zhquad) |
+| Bleu_3           |   85.52 | default | [lmqg/qg_zhquad](https://huggingface.co/datasets/lmqg/qg_zhquad) |
+| Bleu_4           |   81.9  | default | [lmqg/qg_zhquad](https://huggingface.co/datasets/lmqg/qg_zhquad) |
+| METEOR           |   69.99 | default | [lmqg/qg_zhquad](https://huggingface.co/datasets/lmqg/qg_zhquad) |
+| MoverScore       |   98.34 | default | [lmqg/qg_zhquad](https://huggingface.co/datasets/lmqg/qg_zhquad) |
+| ROUGE_L          |   95.05 | 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-small
+ - max_length: 512
+ - max_length_output: 32
+ - epoch: 13
+ - batch: 16
+ - lr: 0.0005
+ - fp16: False
+ - random_seed: 1
+ - gradient_accumulation_steps: 4
+ - label_smoothing: 0.15
+
+The full configuration can be found at [fine-tuning config file](https://huggingface.co/lmqg/mt5-small-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",
+}
+
+```

eval/metric.first.answer.paragraph.questions_answers.lmqg_qg_zhquad.default.json

@@ -0,0 +1 @@
+{"test": {"QAAlignedF1Score (BERTScore)": 0.7855418210382505, "QAAlignedRecall (BERTScore)": 0.8208603804685184, "QAAlignedPrecision (BERTScore)": 0.7540897454058011, "QAAlignedF1Score (MoverScore)": 0.5346857464613931, "QAAlignedRecall (MoverScore)": 0.5573226932786458, "QAAlignedPrecision (MoverScore)": 0.5149503046336772, "Bleu_1": 0.0041614176413362495, "Bleu_2": 0.0002733861561829292, "Bleu_3": 2.340360147027646e-09, "Bleu_4": 6.888798702454551e-12, "METEOR": 0.18429060924552587, "ROUGE_L": 0.00845788063698488, "BERTScore": 0.6414252227800591, "MoverScore": 0.5141970065432502}, "validation": {"QAAlignedF1Score (BERTScore)": 0.7789481114021237, "QAAlignedRecall (BERTScore)": 0.7934471714686923, "QAAlignedPrecision (BERTScore)": 0.7658980201047756, "QAAlignedF1Score (MoverScore)": 0.5278587637995821, "QAAlignedRecall (MoverScore)": 0.5360172284317156, "QAAlignedPrecision (MoverScore)": 0.5205962308310392, "Bleu_1": 0.02065945599546766, "Bleu_2": 0.002552676017681431, "Bleu_3": 1.901519885362209e-08, "Bleu_4": 5.2356373782118696e-11, "METEOR": 0.22093221593656595, "ROUGE_L": 0.03587313290341381, "BERTScore": 0.7149331729339831, "MoverScore": 0.5313016230989522}}

eval/metric.first.answer.paragraph_answer.question.lmqg_qg_zhquad.default.json

@@ -0,0 +1 @@
+{"validation": {"Bleu_1": 0.3124483107517401, "Bleu_2": 0.2022414212638196, "Bleu_3": 0.14075126599752, "Bleu_4": 0.10182666104520205}, "test": {"Bleu_1": 0.3501257943333252, "Bleu_2": 0.24440639411446236, "Bleu_3": 0.18147864275298717, "Bleu_4": 0.13947640671540798}}

eval/metric.first.answer.paragraph_sentence.answer.lmqg_qg_zhquad.default.json

@@ -0,0 +1 @@
+{"validation": {"Bleu_1": 0.8984976332578349, "Bleu_2": 0.863700476581162, "Bleu_3": 0.8282907154192872, "Bleu_4": 0.7920031456423521, "METEOR": 0.6806077153375327, "ROUGE_L": 0.9354048878527517, "BERTScore": 0.9926965533420552, "MoverScore": 0.9717035876046614, "AnswerF1Score": 91.1079696570226, "AnswerExactMatch": 90.95434677027683}, "test": {"Bleu_1": 0.919962455736127, "Bleu_2": 0.8887173195119843, "Bleu_3": 0.8551528572574789, "Bleu_4": 0.8190150316147392, "METEOR": 0.6998790171093476, "ROUGE_L": 0.9505111691582052, "BERTScore": 0.9968959816223559, "MoverScore": 0.9834331628286197, "AnswerF1Score": 93.57801984319713, "AnswerExactMatch": 93.50412821758135}}

eval/metric.first.sentence.paragraph_answer.question.lmqg_qg_zhquad.default.json

@@ -0,0 +1 @@
+{"validation": {"Bleu_1": 0.33373569071875603, "Bleu_2": 0.2185563962082155, "Bleu_3": 0.1535138754584376, "Bleu_4": 0.11187321831967545, "METEOR": 0.21087463407744778, "ROUGE_L": 0.30035405539883947, "BERTScore": 0.7462091987138463, "MoverScore": 0.5583120385347042}, "test": {"Bleu_1": 0.35243536991633617, "Bleu_2": 0.2455785473109513, "Bleu_3": 0.1820979479554548, "Bleu_4": 0.13977943479979163, "METEOR": 0.2288054594770842, "ROUGE_L": 0.33168122312199494, "BERTScore": 0.7664240089175756, "MoverScore": 0.5703214083124712}}