README.md

---
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",
}

```