Edit model card

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

This model is fine-tuned version of google/mt5-base 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-base-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-base-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 81.16 default lmqg/qg_itquad
Bleu_1 23.29 default lmqg/qg_itquad
Bleu_2 15.37 default lmqg/qg_itquad
Bleu_3 10.72 default lmqg/qg_itquad
Bleu_4 7.7 default lmqg/qg_itquad
METEOR 18 default lmqg/qg_itquad
MoverScore 57.11 default lmqg/qg_itquad
ROUGE_L 22.51 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) 87.93 default lmqg/qg_itquad
QAAlignedF1Score (MoverScore) 61.91 default lmqg/qg_itquad
QAAlignedPrecision (BERTScore) 88.02 default lmqg/qg_itquad
QAAlignedPrecision (MoverScore) 62.04 default lmqg/qg_itquad
QAAlignedRecall (BERTScore) 87.84 default lmqg/qg_itquad
QAAlignedRecall (MoverScore) 61.78 default lmqg/qg_itquad
Score Type Dataset
QAAlignedF1Score (BERTScore) 81.68 default lmqg/qg_itquad
QAAlignedF1Score (MoverScore) 55.83 default lmqg/qg_itquad
QAAlignedPrecision (BERTScore) 81.25 default lmqg/qg_itquad
QAAlignedPrecision (MoverScore) 55.68 default lmqg/qg_itquad
QAAlignedRecall (BERTScore) 82.16 default lmqg/qg_itquad
QAAlignedRecall (MoverScore) 56.01 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-base
  • max_length: 512
  • max_length_output: 32
  • epoch: 11
  • batch: 4
  • lr: 0.001
  • fp16: False
  • random_seed: 1
  • gradient_accumulation_steps: 16
  • 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
32
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.

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

Evaluation results

  • BLEU4 (Question Generation) on lmqg/qg_itquad
    self-reported
    7.700
  • ROUGE-L (Question Generation) on lmqg/qg_itquad
    self-reported
    22.510
  • METEOR (Question Generation) on lmqg/qg_itquad
    self-reported
    18.000
  • BERTScore (Question Generation) on lmqg/qg_itquad
    self-reported
    81.160
  • MoverScore (Question Generation) on lmqg/qg_itquad
    self-reported
    57.110
  • QAAlignedF1Score-BERTScore (Question & Answer Generation (with Gold Answer)) [Gold Answer] on lmqg/qg_itquad
    self-reported
    87.930
  • QAAlignedRecall-BERTScore (Question & Answer Generation (with Gold Answer)) [Gold Answer] on lmqg/qg_itquad
    self-reported
    87.840
  • QAAlignedPrecision-BERTScore (Question & Answer Generation (with Gold Answer)) [Gold Answer] on lmqg/qg_itquad
    self-reported
    88.020
  • QAAlignedF1Score-MoverScore (Question & Answer Generation (with Gold Answer)) [Gold Answer] on lmqg/qg_itquad
    self-reported
    61.910
  • QAAlignedRecall-MoverScore (Question & Answer Generation (with Gold Answer)) [Gold Answer] on lmqg/qg_itquad
    self-reported
    61.780