Edit model card

Model Card of lmqg/mt5-small-itquad-qg

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

Overview

Usage

from lmqg import TransformersQG

# initialize model
model = TransformersQG(language="it", model="lmqg/mt5-small-itquad-qg")

# model prediction
questions = model.generate_q(list_context="Dopo il 1971 , l' OPEC ha tardato ad adeguare i prezzi per riflettere tale deprezzamento.", list_answer="Dopo il 1971")
  • With transformers
from transformers import pipeline

pipe = pipeline("text2text-generation", "lmqg/mt5-small-itquad-qg")
output = pipe("<hl> Dopo il 1971 <hl> , l' OPEC ha tardato ad adeguare i prezzi per riflettere tale deprezzamento.")

Evaluation

Score Type Dataset
BERTScore 80.8 default lmqg/qg_itquad
Bleu_1 22.78 default lmqg/qg_itquad
Bleu_2 14.93 default lmqg/qg_itquad
Bleu_3 10.34 default lmqg/qg_itquad
Bleu_4 7.37 default lmqg/qg_itquad
METEOR 17.57 default lmqg/qg_itquad
MoverScore 56.79 default lmqg/qg_itquad
ROUGE_L 21.93 default lmqg/qg_itquad
  • Metric (Question & Answer Generation, Reference Answer): Each question is generated from the gold answer. raw metric file
Score Type Dataset
QAAlignedF1Score (BERTScore) 87.66 default lmqg/qg_itquad
QAAlignedF1Score (MoverScore) 61.6 default lmqg/qg_itquad
QAAlignedPrecision (BERTScore) 87.76 default lmqg/qg_itquad
QAAlignedPrecision (MoverScore) 61.73 default lmqg/qg_itquad
QAAlignedRecall (BERTScore) 87.57 default lmqg/qg_itquad
QAAlignedRecall (MoverScore) 61.48 default lmqg/qg_itquad
Score Type Dataset
QAAlignedF1Score (BERTScore) 81.63 default lmqg/qg_itquad
QAAlignedF1Score (MoverScore) 55.85 default lmqg/qg_itquad
QAAlignedPrecision (BERTScore) 81.04 default lmqg/qg_itquad
QAAlignedPrecision (MoverScore) 55.6 default lmqg/qg_itquad
QAAlignedRecall (BERTScore) 82.28 default lmqg/qg_itquad
QAAlignedRecall (MoverScore) 56.14 default lmqg/qg_itquad

Training hyperparameters

The following hyperparameters were used during fine-tuning:

  • dataset_path: lmqg/qg_itquad
  • 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: 15
  • batch: 16
  • lr: 0.0005
  • fp16: False
  • random_seed: 1
  • gradient_accumulation_steps: 4
  • 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",
}
Downloads last month
4

Dataset used to train lmqg/mt5-small-itquad-qg

Evaluation results

  • BLEU4 (Question Generation) on lmqg/qg_itquad
    self-reported
    7.370
  • ROUGE-L (Question Generation) on lmqg/qg_itquad
    self-reported
    21.930
  • METEOR (Question Generation) on lmqg/qg_itquad
    self-reported
    17.570
  • BERTScore (Question Generation) on lmqg/qg_itquad
    self-reported
    80.800
  • MoverScore (Question Generation) on lmqg/qg_itquad
    self-reported
    56.790
  • QAAlignedF1Score-BERTScore (Question & Answer Generation (with Gold Answer)) [Gold Answer] on lmqg/qg_itquad
    self-reported
    87.660
  • QAAlignedRecall-BERTScore (Question & Answer Generation (with Gold Answer)) [Gold Answer] on lmqg/qg_itquad
    self-reported
    87.570
  • QAAlignedPrecision-BERTScore (Question & Answer Generation (with Gold Answer)) [Gold Answer] on lmqg/qg_itquad
    self-reported
    87.760
  • QAAlignedF1Score-MoverScore (Question & Answer Generation (with Gold Answer)) [Gold Answer] on lmqg/qg_itquad
    self-reported
    61.600
  • QAAlignedRecall-MoverScore (Question & Answer Generation (with Gold Answer)) [Gold Answer] on lmqg/qg_itquad
    self-reported
    61.480
  • QAAlignedPrecision-MoverScore (Question & Answer Generation (with Gold Answer)) [Gold Answer] on lmqg/qg_itquad
    self-reported
    61.730
  • QAAlignedF1Score-BERTScore (Question & Answer Generation) [Gold Answer] on lmqg/qg_itquad
    self-reported
    81.630
  • QAAlignedRecall-BERTScore (Question & Answer Generation) [Gold Answer] on lmqg/qg_itquad
    self-reported
    82.280
  • QAAlignedPrecision-BERTScore (Question & Answer Generation) [Gold Answer] on lmqg/qg_itquad
    self-reported
    81.040
  • QAAlignedF1Score-MoverScore (Question & Answer Generation) [Gold Answer] on lmqg/qg_itquad
    self-reported
    55.850
  • QAAlignedRecall-MoverScore (Question & Answer Generation) [Gold Answer] on lmqg/qg_itquad
    self-reported
    56.140
  • QAAlignedPrecision-MoverScore (Question & Answer Generation) [Gold Answer] on lmqg/qg_itquad
    self-reported
    55.600