asahi417's picture
commit files to HF hub
eb21aeb
---
license: cc-by-4.0
metrics:
- bleu4
- meteor
- rouge-l
- bertscore
- moverscore
language: ko
datasets:
- lmqg/qg_koquad
pipeline_tag: text2text-generation
tags:
- question generation
widget:
- text: "1990년 영화 《 <hl> 남부군 <hl> 》에서 단역으로 영화배우 첫 데뷔에 이어 같은 해 KBS 드라마 《지구인》에서 단역으로 출연하였고 이듬해 MBC 《여명의 눈동자》를 통해 단역으로 출연하였다."
example_title: "Question Generation Example 1"
- text: "백신이 없기때문에 예방책은 <hl> 살충제 <hl> 를 사용하면서 서식 장소(찻찬 받침, 배수로, 고인 물의 열린 저장소, 버려진 타이어 등)의 수를 줄임으로써 매개체를 통제할 수 있다."
example_title: "Question Generation Example 2"
- text: "<hl> 원테이크 촬영 <hl> 이기 때문에 한 사람이 실수를 하면 처음부터 다시 찍어야 하는 상황이 발생한다."
example_title: "Question Generation Example 3"
model-index:
- name: vocabtrimmer/mt5-small-trimmed-ko-30000-koquad-qg
results:
- task:
name: Text2text Generation
type: text2text-generation
dataset:
name: lmqg/qg_koquad
type: default
args: default
metrics:
- name: BLEU4 (Question Generation)
type: bleu4_question_generation
value: 10.99
- name: ROUGE-L (Question Generation)
type: rouge_l_question_generation
value: 26.81
- name: METEOR (Question Generation)
type: meteor_question_generation
value: 28.76
- name: BERTScore (Question Generation)
type: bertscore_question_generation
value: 83.39
- name: MoverScore (Question Generation)
type: moverscore_question_generation
value: 83.1
---
# Model Card of `vocabtrimmer/mt5-small-trimmed-ko-30000-koquad-qg`
This model is fine-tuned version of [ckpts/mt5-small-trimmed-ko-30000](https://huggingface.co/ckpts/mt5-small-trimmed-ko-30000) for question generation task on the [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) (dataset_name: default) via [`lmqg`](https://github.com/asahi417/lm-question-generation).
### Overview
- **Language model:** [ckpts/mt5-small-trimmed-ko-30000](https://huggingface.co/ckpts/mt5-small-trimmed-ko-30000)
- **Language:** ko
- **Training data:** [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) (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="ko", model="vocabtrimmer/mt5-small-trimmed-ko-30000-koquad-qg")
# model prediction
questions = model.generate_q(list_context="1990년 영화 《 남부군 》에서 단역으로 영화배우 첫 데뷔에 이어 같은 해 KBS 드라마 《지구인》에서 단역으로 출연하였고 이듬해 MBC 《여명의 눈동자》를 통해 단역으로 출연하였다.", list_answer="남부군")
```
- With `transformers`
```python
from transformers import pipeline
pipe = pipeline("text2text-generation", "vocabtrimmer/mt5-small-trimmed-ko-30000-koquad-qg")
output = pipe("1990년 영화 《 <hl> 남부군 <hl> 》에서 단역으로 영화배우 첫 데뷔에 이어 같은 해 KBS 드라마 《지구인》에서 단역으로 출연하였고 이듬해 MBC 《여명의 눈동자》를 통해 단역으로 출연하였다.")
```
## Evaluation
- ***Metric (Question Generation)***: [raw metric file](https://huggingface.co/vocabtrimmer/mt5-small-trimmed-ko-30000-koquad-qg/raw/main/eval/metric.first.sentence.paragraph_answer.question.lmqg_qg_koquad.default.json)
| | Score | Type | Dataset |
|:-----------|--------:|:--------|:-----------------------------------------------------------------|
| BERTScore | 83.39 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
| Bleu_1 | 26.37 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
| Bleu_2 | 19.37 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
| Bleu_3 | 14.53 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
| Bleu_4 | 10.99 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
| METEOR | 28.76 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
| MoverScore | 83.1 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
| ROUGE_L | 26.81 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
## Training hyperparameters
The following hyperparameters were used during fine-tuning:
- dataset_path: lmqg/qg_koquad
- dataset_name: default
- input_types: paragraph_answer
- output_types: question
- prefix_types: None
- model: ckpts/mt5-small-trimmed-ko-30000
- max_length: 512
- max_length_output: 32
- epoch: 16
- batch: 64
- lr: 0.001
- fp16: False
- random_seed: 1
- gradient_accumulation_steps: 1
- label_smoothing: 0.15
The full configuration can be found at [fine-tuning config file](https://huggingface.co/vocabtrimmer/mt5-small-trimmed-ko-30000-koquad-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",
}
```