Edit model card

Model Card of lmqg/mt5-small-esquad-qg-ae

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

Overview

Usage

from lmqg import TransformersQG

# initialize model
model = TransformersQG(language="es", model="lmqg/mt5-small-esquad-qg-ae")

# model prediction
question_answer_pairs = model.generate_qa("a noviembre , que es también la estación lluviosa.")
  • With transformers
from transformers import pipeline

pipe = pipeline("text2text-generation", "lmqg/mt5-small-esquad-qg-ae")

# answer extraction
answer = pipe("generate question: del <hl> Ministerio de Desarrollo Urbano <hl> , Gobierno de la India.")

# question generation
question = pipe("extract answers: <hl> En la diáspora somalí, múltiples eventos islámicos de recaudación de fondos se llevan a cabo cada año en ciudades como Birmingham, Londres, Toronto y Minneapolis, donde los académicos y profesionales somalíes dan conferencias y responden preguntas de la audiencia. <hl> El propósito de estos eventos es recaudar dinero para nuevas escuelas o universidades en Somalia, para ayudar a los somalíes que han sufrido como consecuencia de inundaciones y / o sequías, o para reunir fondos para la creación de nuevas mezquitas como.")

Evaluation

Score Type Dataset
BERTScore 83.39 default lmqg/qg_esquad
Bleu_1 24.5 default lmqg/qg_esquad
Bleu_2 16.48 default lmqg/qg_esquad
Bleu_3 11.83 default lmqg/qg_esquad
Bleu_4 8.79 default lmqg/qg_esquad
METEOR 21.66 default lmqg/qg_esquad
MoverScore 58.34 default lmqg/qg_esquad
ROUGE_L 23.13 default lmqg/qg_esquad
Score Type Dataset
QAAlignedF1Score (BERTScore) 79.06 default lmqg/qg_esquad
QAAlignedF1Score (MoverScore) 54.49 default lmqg/qg_esquad
QAAlignedPrecision (BERTScore) 76.46 default lmqg/qg_esquad
QAAlignedPrecision (MoverScore) 52.96 default lmqg/qg_esquad
QAAlignedRecall (BERTScore) 81.94 default lmqg/qg_esquad
QAAlignedRecall (MoverScore) 56.21 default lmqg/qg_esquad
Score Type Dataset
AnswerExactMatch 57.63 default lmqg/qg_esquad
AnswerF1Score 75.31 default lmqg/qg_esquad
BERTScore 89.77 default lmqg/qg_esquad
Bleu_1 35.18 default lmqg/qg_esquad
Bleu_2 30.48 default lmqg/qg_esquad
Bleu_3 26.92 default lmqg/qg_esquad
Bleu_4 23.89 default lmqg/qg_esquad
METEOR 43.11 default lmqg/qg_esquad
MoverScore 80.64 default lmqg/qg_esquad
ROUGE_L 48.58 default lmqg/qg_esquad

Training hyperparameters

The following hyperparameters were used during fine-tuning:

  • dataset_path: lmqg/qg_esquad
  • dataset_name: default
  • input_types: ['paragraph_answer', 'paragraph_sentence']
  • output_types: ['question', 'answer']
  • prefix_types: ['qg', 'ae']
  • model: google/mt5-small
  • max_length: 512
  • max_length_output: 32
  • epoch: 5
  • batch: 16
  • lr: 0.001
  • fp16: False
  • random_seed: 1
  • gradient_accumulation_steps: 4
  • 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
147

Dataset used to train lmqg/mt5-small-esquad-qg-ae

Evaluation results

  • BLEU4 (Question Generation) on lmqg/qg_esquad
    self-reported
    8.790
  • ROUGE-L (Question Generation) on lmqg/qg_esquad
    self-reported
    23.130
  • METEOR (Question Generation) on lmqg/qg_esquad
    self-reported
    21.660
  • BERTScore (Question Generation) on lmqg/qg_esquad
    self-reported
    83.390
  • MoverScore (Question Generation) on lmqg/qg_esquad
    self-reported
    58.340
  • QAAlignedF1Score-BERTScore (Question & Answer Generation (with Gold Answer)) on lmqg/qg_esquad
    self-reported
    79.060
  • QAAlignedRecall-BERTScore (Question & Answer Generation (with Gold Answer)) on lmqg/qg_esquad
    self-reported
    81.940
  • QAAlignedPrecision-BERTScore (Question & Answer Generation (with Gold Answer)) on lmqg/qg_esquad
    self-reported
    76.460
  • QAAlignedF1Score-MoverScore (Question & Answer Generation (with Gold Answer)) on lmqg/qg_esquad
    self-reported
    54.490
  • QAAlignedRecall-MoverScore (Question & Answer Generation (with Gold Answer)) on lmqg/qg_esquad
    self-reported
    56.210
  • QAAlignedPrecision-MoverScore (Question & Answer Generation (with Gold Answer)) on lmqg/qg_esquad
    self-reported
    52.960
  • BLEU4 (Answer Extraction) on lmqg/qg_esquad
    self-reported
    23.890
  • ROUGE-L (Answer Extraction) on lmqg/qg_esquad
    self-reported
    48.580
  • METEOR (Answer Extraction) on lmqg/qg_esquad
    self-reported
    43.110
  • BERTScore (Answer Extraction) on lmqg/qg_esquad
    self-reported
    89.770
  • MoverScore (Answer Extraction) on lmqg/qg_esquad
    self-reported
    80.640
  • AnswerF1Score (Answer Extraction) on lmqg/qg_esquad
    self-reported
    75.310
  • AnswerExactMatch (Answer Extraction) on lmqg/qg_esquad
    self-reported
    57.630