Model Card of lmqg/mt5-small-zhquad-qag

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

Overview

• Language model: google/mt5-small
• Language: zh
• Training data: lmqg/qag_zhquad (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="zh", model="lmqg/mt5-small-zhquad-qag")

# 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

from transformers import pipeline

pipe = pipeline("text2text-generation", "lmqg/mt5-small-zhquad-qag")
output = pipe("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。")

Evaluation

• Metric (Question & Answer Generation): raw metric file

	Score	Type	Dataset
QAAlignedF1Score (BERTScore)	75.47	default	lmqg/qag_zhquad
QAAlignedF1Score (MoverScore)	52.42	default	lmqg/qag_zhquad
QAAlignedPrecision (BERTScore)	75.56	default	lmqg/qag_zhquad
QAAlignedPrecision (MoverScore)	52.53	default	lmqg/qag_zhquad
QAAlignedRecall (BERTScore)	75.41	default	lmqg/qag_zhquad
QAAlignedRecall (MoverScore)	52.33	default	lmqg/qag_zhquad

Training hyperparameters

The following hyperparameters were used during fine-tuning:

• dataset_path: lmqg/qag_zhquad
• 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: 12
• batch: 8
• lr: 0.001
• fp16: False
• random_seed: 1
• gradient_accumulation_steps: 8
• 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",
}