lmqg/mt5-base-koquad-qag

license: cc-by-4.0 metrics:

• —bleu4
• —meteor
• —rouge-l
• —bertscore
• —moverscore language: ko datasets:
• —lmqg/qagkoquad pipelinetag: text2text-generation tags:
• —questions and answers generation widget:
• —text: "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." example_title: "Questions & Answers Generation Example 1" model-index:
• —name: lmqg/mt5-base-koquad-qag results:
• —task: name: Text2text Generation type: text2text-generation dataset: name: lmqg/qag_koquad type: default args: default metrics:
• —name: QAAlignedF1Score-BERTScore (Question & Answer Generation) type: qaalignedf1scorebertscorequestionanswer_generation value: 76.88
• —name: QAAlignedRecall-BERTScore (Question & Answer Generation) type: qaalignedrecallbertscorequestionanswergeneration value: 76.69
• —name: QAAlignedPrecision-BERTScore (Question & Answer Generation) type: qaalignedprecisionbertscorequestionanswergeneration value: 77.1
• —name: QAAlignedF1Score-MoverScore (Question & Answer Generation) type: qaalignedf1scoremoverscorequestionanswer_generation value: 77.95
• —name: QAAlignedRecall-MoverScore (Question & Answer Generation) type: qaalignedrecallmoverscorequestionanswergeneration value: 77.66
• —name: QAAlignedPrecision-MoverScore (Question & Answer Generation) type: qaalignedprecisionmoverscorequestionanswergeneration value: 78.29 ---

Model Card of lmqg/mt5-base-koquad-qag

This model is fine-tuned version of google/mt5-base for question & answer pair generation task on the lmqg/qag_koquad (dataset_name: default) via `lmqg`.

Overview

• —Language model: google/mt5-base
• —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/mt5-base-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/mt5-base-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

Training hyperparameters

The following hyperparameters were used during fine-tuning:

• —datasetpath: lmqg/qagkoquad
• —dataset_name: default
• —input_types: ['paragraph']
• —outputtypes: ['questionsanswers']
• —prefix_types: None
• —model: google/mt5-base
• —max_length: 512
• —maxlengthoutput: 256
• —epoch: 18
• —batch: 2
• —lr: 0.001
• —fp16: False
• —random_seed: 1
• —gradientaccumulationsteps: 64
• —label_smoothing: 0.15

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",
}