metadata

license: cc-by-4.0
metrics:
  - bleu4
  - meteor
  - rouge-l
  - bertscore
  - moverscore
language: fr
datasets:
  - lmqg/qg_frquad
pipeline_tag: text2text-generation
tags:
  - question generation
widget:
  - text: >-
      Créateur » (Maker), lui aussi au singulier, « <hl> le Suprême Berger <hl>
      » (The Great Shepherd) ; de l'autre, des réminiscences de la théologie de
      l'Antiquité : le tonnerre, voix de Jupiter, « Et souvent ta voix gronde en
      un tonnerre terrifiant », etc.
    example_title: Question Generation Example 1
  - text: >-
      Ce black dog peut être lié à des évènements traumatisants issus du monde
      extérieur, tels que son renvoi de l'Amirauté après la catastrophe des
      Dardanelles, lors de la <hl> Grande Guerre <hl> de 14-18, ou son rejet par
      l'électorat en juillet 1945.
    example_title: Question Generation Example 2
  - text: contre <hl> Normie Smith <hl> et 15 000 dollars le 28 novembre 1938.
    example_title: Question Generation Example 3
model-index:
  - name: lmqg/mt5-small-frquad-qg
    results:
      - task:
          name: Text2text Generation
          type: text2text-generation
        dataset:
          name: lmqg/qg_frquad
          type: default
          args: default
        metrics:
          - name: BLEU4 (Question Generation)
            type: bleu4_question_generation
            value: 8.55
          - name: ROUGE-L (Question Generation)
            type: rouge_l_question_generation
            value: 28.56
          - name: METEOR (Question Generation)
            type: meteor_question_generation
            value: 17.51
          - name: BERTScore (Question Generation)
            type: bertscore_question_generation
            value: 80.71
          - name: MoverScore (Question Generation)
            type: moverscore_question_generation
            value: 56.5
          - name: BLEU4 (Question & Answer Generation)
            type: bleu4_question_answer_generation
            value: 13.83
          - name: ROUGE-L (Question & Answer Generation)
            type: rouge_l_question_answer_generation
            value: 42.57
          - name: METEOR (Question & Answer Generation)
            type: meteor_question_answer_generation
            value: 34.29
          - name: BERTScore (Question & Answer Generation)
            type: bertscore_question_answer_generation
            value: 88.51
          - name: MoverScore (Question & Answer Generation)
            type: moverscore_question_answer_generation
            value: 62.42
          - name: >-
              QAAlignedF1Score-BERTScore (Question & Answer Generation) [Gold
              Answer]
            type: >-
              qa_aligned_f1_score_bertscore_question_answer_generation_gold_answer
            value: 88.52
          - name: >-
              QAAlignedRecall-BERTScore (Question & Answer Generation) [Gold
              Answer]
            type: qa_aligned_recall_bertscore_question_answer_generation_gold_answer
            value: 88.51
          - name: >-
              QAAlignedPrecision-BERTScore (Question & Answer Generation) [Gold
              Answer]
            type: >-
              qa_aligned_precision_bertscore_question_answer_generation_gold_answer
            value: 88.53
          - name: >-
              QAAlignedF1Score-MoverScore (Question & Answer Generation) [Gold
              Answer]
            type: >-
              qa_aligned_f1_score_moverscore_question_answer_generation_gold_answer
            value: 62.46
          - name: >-
              QAAlignedRecall-MoverScore (Question & Answer Generation) [Gold
              Answer]
            type: >-
              qa_aligned_recall_moverscore_question_answer_generation_gold_answer
            value: 62.45
          - name: >-
              QAAlignedPrecision-MoverScore (Question & Answer Generation) [Gold
              Answer]
            type: >-
              qa_aligned_precision_moverscore_question_answer_generation_gold_answer
            value: 62.46

Model Card of `lmqg/mt5-small-frquad-qg`

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

Overview

Language model: google/mt5-small
Language: fr
Training data: lmqg/qg_frquad (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="fr", model="lmqg/mt5-small-frquad-qg")

# model prediction
questions = model.generate_q(list_context="Créateur » (Maker), lui aussi au singulier, « le Suprême Berger » (The Great Shepherd) ; de l'autre, des réminiscences de la théologie de l'Antiquité : le tonnerre, voix de Jupiter, « Et souvent ta voix gronde en un tonnerre terrifiant », etc.", list_answer="le Suprême Berger")

With transformers

from transformers import pipeline

pipe = pipeline("text2text-generation", "lmqg/mt5-small-frquad-qg")
output = pipe("Créateur » (Maker), lui aussi au singulier, « <hl> le Suprême Berger <hl> » (The Great Shepherd) ; de l'autre, des réminiscences de la théologie de l'Antiquité : le tonnerre, voix de Jupiter, « Et souvent ta voix gronde en un tonnerre terrifiant », etc.")

Evaluation

Metric (Question Generation): raw metric file

	Score	Type	Dataset
BERTScore	80.71	default	lmqg/qg_frquad
Bleu_1	29.26	default	lmqg/qg_frquad
Bleu_2	17.56	default	lmqg/qg_frquad
Bleu_3	12.03	default	lmqg/qg_frquad
Bleu_4	8.55	default	lmqg/qg_frquad
METEOR	17.51	default	lmqg/qg_frquad
MoverScore	56.5	default	lmqg/qg_frquad
ROUGE_L	28.56	default	lmqg/qg_frquad

Metric (Question & Answer Generation): QAG metrics are computed with the gold answer and generated question on it for this model, as the model cannot provide an answer. raw metric file

	Score	Type	Dataset
BERTScore	88.51	default	lmqg/qg_frquad
Bleu_1	39.78	default	lmqg/qg_frquad
Bleu_2	27.56	default	lmqg/qg_frquad
Bleu_3	19.54	default	lmqg/qg_frquad
Bleu_4	13.83	default	lmqg/qg_frquad
METEOR	34.29	default	lmqg/qg_frquad
MoverScore	62.42	default	lmqg/qg_frquad
QAAlignedF1Score (BERTScore)	88.52	default	lmqg/qg_frquad
QAAlignedF1Score (MoverScore)	62.46	default	lmqg/qg_frquad
QAAlignedPrecision (BERTScore)	88.53	default	lmqg/qg_frquad
QAAlignedPrecision (MoverScore)	62.46	default	lmqg/qg_frquad
QAAlignedRecall (BERTScore)	88.51	default	lmqg/qg_frquad
QAAlignedRecall (MoverScore)	62.45	default	lmqg/qg_frquad
ROUGE_L	42.57	default	lmqg/qg_frquad

Training hyperparameters

The following hyperparameters were used during fine-tuning:

dataset_path: lmqg/qg_frquad
dataset_name: default
input_types: ['paragraph_answer']
output_types: ['question']
prefix_types: None
model: google/mt5-small
max_length: 512
max_length_output: 32
epoch: 14
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.

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",
}