Model Card of lmqg/mbart-large-cc25-koquad-qag
This model is fine-tuned version of facebook/mbart-large-cc25 for question & answer pair generation task on the lmqg/qag_koquad (dataset_name: default) via lmqg
.
Overview
- Language model: facebook/mbart-large-cc25
- Language: ko
- Training data: lmqg/qag_koquad (default)
- Online Demo: https://autoqg.net/
- Repository: https://github.com/asahi417/lm-question-generation
- Paper: https://arxiv.org/abs/2210.03992
Usage
- With
lmqg
from lmqg import TransformersQG
# initialize model
model = TransformersQG(language="ko", model="lmqg/mbart-large-cc25-koquad-qag")
# model prediction
question_answer_pairs = model.generate_qa("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.")
- With
transformers
from transformers import pipeline
pipe = pipeline("text2text-generation", "lmqg/mbart-large-cc25-koquad-qag")
output = pipe("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.")
Evaluation
- Metric (Question & Answer Generation): raw metric file
Score | Type | Dataset | |
---|---|---|---|
QAAlignedF1Score (BERTScore) | 80.71 | default | lmqg/qag_koquad |
QAAlignedF1Score (MoverScore) | 81.75 | default | lmqg/qag_koquad |
QAAlignedPrecision (BERTScore) | 78.58 | default | lmqg/qag_koquad |
QAAlignedPrecision (MoverScore) | 79.01 | default | lmqg/qag_koquad |
QAAlignedRecall (BERTScore) | 83.05 | default | lmqg/qag_koquad |
QAAlignedRecall (MoverScore) | 84.86 | default | lmqg/qag_koquad |
Training hyperparameters
The following hyperparameters were used during fine-tuning:
- dataset_path: lmqg/qag_koquad
- dataset_name: default
- input_types: ['paragraph']
- output_types: ['questions_answers']
- prefix_types: None
- model: facebook/mbart-large-cc25
- max_length: 512
- max_length_output: 256
- epoch: 11
- batch: 2
- lr: 0.0001
- fp16: False
- random_seed: 1
- gradient_accumulation_steps: 32
- label_smoothing: 0.0
The full configuration can be found at fine-tuning config file.
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",
}
- Downloads last month
- 8
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Dataset used to train research-backup/mbart-large-cc25-koquad-qag
Evaluation results
- QAAlignedF1Score-BERTScore (Question & Answer Generation) on lmqg/qag_koquadself-reported80.710
- QAAlignedRecall-BERTScore (Question & Answer Generation) on lmqg/qag_koquadself-reported83.050
- QAAlignedPrecision-BERTScore (Question & Answer Generation) on lmqg/qag_koquadself-reported78.580
- QAAlignedF1Score-MoverScore (Question & Answer Generation) on lmqg/qag_koquadself-reported81.750
- QAAlignedRecall-MoverScore (Question & Answer Generation) on lmqg/qag_koquadself-reported84.860
- QAAlignedPrecision-MoverScore (Question & Answer Generation) on lmqg/qag_koquadself-reported79.010