metadata

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 for question & answer pair generation task on the lmqg/qag_jaquad (dataset_name: default) via lmqg.

Overview

Language model: google/mt5-small
Language: ja
Training data: lmqg/qag_jaquad (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="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

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

	Score	Type	Dataset
BERTScore	58.55	default	lmqg/qag_jaquad
Bleu_1	8.16	default	lmqg/qag_jaquad
Bleu_2	6.13	default	lmqg/qag_jaquad
Bleu_3	4.7	default	lmqg/qag_jaquad
Bleu_4	3.66	default	lmqg/qag_jaquad
METEOR	9.88	default	lmqg/qag_jaquad
MoverScore	49.1	default	lmqg/qag_jaquad
QAAlignedF1Score (BERTScore)	58.35	default	lmqg/qag_jaquad
QAAlignedF1Score (MoverScore)	39.19	default	lmqg/qag_jaquad
QAAlignedPrecision (BERTScore)	58.34	default	lmqg/qag_jaquad
QAAlignedPrecision (MoverScore)	39.21	default	lmqg/qag_jaquad
QAAlignedRecall (BERTScore)	58.38	default	lmqg/qag_jaquad
QAAlignedRecall (MoverScore)	39.17	default	lmqg/qag_jaquad
ROUGE_L	15.62	default	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.

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",
}