Model Card of lmqg/mt5-base-frquad-qg-ae

This model is fine-tuned version of google/mt5-base for question generation and answer extraction jointly on the lmqg/qg_frquad (dataset_name: default) via lmqg.

Overview

Usage

from lmqg import TransformersQG

# initialize model
model = TransformersQG(language="fr", model="lmqg/mt5-base-frquad-qg-ae")

# model prediction
question_answer_pairs = model.generate_qa("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.")
  • With transformers
from transformers import pipeline

pipe = pipeline("text2text-generation", "lmqg/mt5-base-frquad-qg-ae")

# answer extraction
answer = pipe("generate question: 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.")

# question generation
question = pipe("extract answers: Pourtant, la strophe spensérienne, utilisée cinq fois avant que ne commence le chœur, constitue en soi un vecteur dont les répétitions structurelles, selon Ricks, relèvent du pur lyrisme tout en constituant une menace potentielle. Après les huit sages pentamètres iambiques, l'alexandrin final <hl> permet une pause <hl>, « véritable illusion d'optique » qu'accentuent les nombreuses expressions archaïsantes telles que did swoon, did seem, did go, did receive, did make, qui doublent le prétérit en un temps composé et paraissent à la fois « très précautionneuses et très peu pressées ».")

Evaluation

Score Type Dataset
BERTScore 79.58 default lmqg/qg_frquad
Bleu_1 27.1 default lmqg/qg_frquad
Bleu_2 15.73 default lmqg/qg_frquad
Bleu_3 10.54 default lmqg/qg_frquad
Bleu_4 7.48 default lmqg/qg_frquad
METEOR 16.7 default lmqg/qg_frquad
MoverScore 55.91 default lmqg/qg_frquad
ROUGE_L 27.05 default lmqg/qg_frquad
Score Type Dataset
QAAlignedF1Score (BERTScore) 79.16 default lmqg/qg_frquad
QAAlignedF1Score (MoverScore) 53.9 default lmqg/qg_frquad
QAAlignedPrecision (BERTScore) 76.69 default lmqg/qg_frquad
QAAlignedPrecision (MoverScore) 52.57 default lmqg/qg_frquad
QAAlignedRecall (BERTScore) 81.87 default lmqg/qg_frquad
QAAlignedRecall (MoverScore) 55.36 default lmqg/qg_frquad
Score Type Dataset
AnswerExactMatch 43.01 default lmqg/qg_frquad
AnswerF1Score 63.54 default lmqg/qg_frquad
BERTScore 86.03 default lmqg/qg_frquad
Bleu_1 35.54 default lmqg/qg_frquad
Bleu_2 30.87 default lmqg/qg_frquad
Bleu_3 27.14 default lmqg/qg_frquad
Bleu_4 23.84 default lmqg/qg_frquad
METEOR 35.22 default lmqg/qg_frquad
MoverScore 73.94 default lmqg/qg_frquad
ROUGE_L 40.94 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', 'paragraph_sentence']
  • output_types: ['question', 'answer']
  • prefix_types: ['qg', 'ae']
  • model: google/mt5-base
  • max_length: 512
  • max_length_output: 32
  • epoch: 15
  • batch: 32
  • lr: 0.001
  • fp16: False
  • random_seed: 1
  • gradient_accumulation_steps: 2
  • 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",
}
Downloads last month
16
Inference Examples
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.

Evaluation results

  • BLEU4 (Question Generation) on lmqg/qg_frquad
    self-reported
    7.480
  • ROUGE-L (Question Generation) on lmqg/qg_frquad
    self-reported
    27.050
  • METEOR (Question Generation) on lmqg/qg_frquad
    self-reported
    16.700
  • BERTScore (Question Generation) on lmqg/qg_frquad
    self-reported
    79.580
  • MoverScore (Question Generation) on lmqg/qg_frquad
    self-reported
    55.910
  • QAAlignedF1Score-BERTScore (Question & Answer Generation (with Gold Answer)) on lmqg/qg_frquad
    self-reported
    79.160
  • QAAlignedRecall-BERTScore (Question & Answer Generation (with Gold Answer)) on lmqg/qg_frquad
    self-reported
    81.870
  • QAAlignedPrecision-BERTScore (Question & Answer Generation (with Gold Answer)) on lmqg/qg_frquad
    self-reported
    76.690
  • QAAlignedF1Score-MoverScore (Question & Answer Generation (with Gold Answer)) on lmqg/qg_frquad
    self-reported
    53.900
  • QAAlignedRecall-MoverScore (Question & Answer Generation (with Gold Answer)) on lmqg/qg_frquad
    self-reported
    55.360