asahi417's picture
model update
3ae3dcc
|
raw
history blame
7.89 kB
---
license: cc-by-4.0
metrics:
- bleu4
- meteor
- rouge-l
- bertscore
- moverscore
language: ja
datasets:
- lmqg/qag_jaquad
pipeline_tag: text2text-generation
tags:
- questions and answers generation
widget:
- text: "ゾフィーは貴族出身ではあったが王族出身ではなく、ハプスブルク家の皇位継承者であるフランツ・フェルディナントとの結婚は貴賤結婚となった。皇帝フランツ・ヨーゼフは、2人の間に生まれた子孫が皇位を継がないことを条件として結婚を承認していた。視察が予定されている6月28日は2人の14回目の結婚記念日であった。"
example_title: "Questions & Answers Generation Example 1"
model-index:
- name: lmqg/mt5-small-jaquad-qag
results:
- task:
name: Text2text Generation
type: text2text-generation
dataset:
name: lmqg/qag_jaquad
type: default
args: default
metrics:
- name: BLEU4 (Question & Answer Generation)
type: bleu4_question_answer_generation
value: 3.66
- name: ROUGE-L (Question & Answer Generation)
type: rouge_l_question_answer_generation
value: 15.62
- name: METEOR (Question & Answer Generation)
type: meteor_question_answer_generation
value: 9.88
- name: BERTScore (Question & Answer Generation)
type: bertscore_question_answer_generation
value: 58.55
- name: MoverScore (Question & Answer Generation)
type: moverscore_question_answer_generation
value: 49.1
- name: QAAlignedF1Score-BERTScore (Question & Answer Generation)
type: qa_aligned_f1_score_bertscore_question_answer_generation
value: 58.35
- name: QAAlignedRecall-BERTScore (Question & Answer Generation)
type: qa_aligned_recall_bertscore_question_answer_generation
value: 58.38
- name: QAAlignedPrecision-BERTScore (Question & Answer Generation)
type: qa_aligned_precision_bertscore_question_answer_generation
value: 58.34
- name: QAAlignedF1Score-MoverScore (Question & Answer Generation)
type: qa_aligned_f1_score_moverscore_question_answer_generation
value: 39.19
- name: QAAlignedRecall-MoverScore (Question & Answer Generation)
type: qa_aligned_recall_moverscore_question_answer_generation
value: 39.17
- name: QAAlignedPrecision-MoverScore (Question & Answer Generation)
type: qa_aligned_precision_moverscore_question_answer_generation
value: 39.21
---
# Model Card of `lmqg/mt5-small-jaquad-qag`
This model is fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) for question & answer pair generation task on the [lmqg/qag_jaquad](https://huggingface.co/datasets/lmqg/qag_jaquad) (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:** ja
- **Training data:** [lmqg/qag_jaquad](https://huggingface.co/datasets/lmqg/qag_jaquad) (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="ja", model="lmqg/mt5-small-jaquad-qag")
# model prediction
question_answer_pairs = model.generate_qa("フェルメールの作品では、17世紀のオランダの画家、ヨハネス・フェルメールの作品について記述する。フェルメールの作品は、疑問作も含め30数点しか現存しない。現存作品はすべて油彩画で、版画、下絵、素描などは残っていない。")
```
- With `transformers`
```python
from transformers import pipeline
pipe = pipeline("text2text-generation", "lmqg/mt5-small-jaquad-qag")
output = pipe("ゾフィーは貴族出身ではあったが王族出身ではなく、ハプスブルク家の皇位継承者であるフランツ・フェルディナントとの結婚は貴賤結婚となった。皇帝フランツ・ヨーゼフは、2人の間に生まれた子孫が皇位を継がないことを条件として結婚を承認していた。視察が予定されている6月28日は2人の14回目の結婚記念日であった。")
```
## Evaluation
- ***Metric (Question & Answer Generation)***: [raw metric file](https://huggingface.co/lmqg/mt5-small-jaquad-qag/raw/main/eval/metric.first.answer.paragraph.questions_answers.lmqg_qag_jaquad.default.json)
| | Score | Type | Dataset |
|:--------------------------------|--------:|:--------|:-------------------------------------------------------------------|
| BERTScore | 58.55 | default | [lmqg/qag_jaquad](https://huggingface.co/datasets/lmqg/qag_jaquad) |
| Bleu_1 | 8.16 | default | [lmqg/qag_jaquad](https://huggingface.co/datasets/lmqg/qag_jaquad) |
| Bleu_2 | 6.13 | default | [lmqg/qag_jaquad](https://huggingface.co/datasets/lmqg/qag_jaquad) |
| Bleu_3 | 4.7 | default | [lmqg/qag_jaquad](https://huggingface.co/datasets/lmqg/qag_jaquad) |
| Bleu_4 | 3.66 | default | [lmqg/qag_jaquad](https://huggingface.co/datasets/lmqg/qag_jaquad) |
| METEOR | 9.88 | default | [lmqg/qag_jaquad](https://huggingface.co/datasets/lmqg/qag_jaquad) |
| MoverScore | 49.1 | default | [lmqg/qag_jaquad](https://huggingface.co/datasets/lmqg/qag_jaquad) |
| QAAlignedF1Score (BERTScore) | 58.35 | default | [lmqg/qag_jaquad](https://huggingface.co/datasets/lmqg/qag_jaquad) |
| QAAlignedF1Score (MoverScore) | 39.19 | default | [lmqg/qag_jaquad](https://huggingface.co/datasets/lmqg/qag_jaquad) |
| QAAlignedPrecision (BERTScore) | 58.34 | default | [lmqg/qag_jaquad](https://huggingface.co/datasets/lmqg/qag_jaquad) |
| QAAlignedPrecision (MoverScore) | 39.21 | default | [lmqg/qag_jaquad](https://huggingface.co/datasets/lmqg/qag_jaquad) |
| QAAlignedRecall (BERTScore) | 58.38 | default | [lmqg/qag_jaquad](https://huggingface.co/datasets/lmqg/qag_jaquad) |
| QAAlignedRecall (MoverScore) | 39.17 | default | [lmqg/qag_jaquad](https://huggingface.co/datasets/lmqg/qag_jaquad) |
| ROUGE_L | 15.62 | default | [lmqg/qag_jaquad](https://huggingface.co/datasets/lmqg/qag_jaquad) |
## Training hyperparameters
The following hyperparameters were used during fine-tuning:
- dataset_path: lmqg/qag_jaquad
- dataset_name: default
- input_types: ['paragraph']
- output_types: ['questions_answers']
- prefix_types: None
- model: google/mt5-small
- max_length: 512
- max_length_output: 256
- epoch: 18
- batch: 8
- lr: 0.001
- fp16: False
- random_seed: 1
- gradient_accumulation_steps: 8
- label_smoothing: 0.0
The full configuration can be found at [fine-tuning config file](https://huggingface.co/lmqg/mt5-small-jaquad-qag/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",
}
```