Model Card of lmqg/mt5-base-ruquad-qag

This model is fine-tuned version of google/mt5-base for question & answer pair generation task on the lmqg/qag_ruquad (dataset_name: default) via lmqg.

Overview

Usage

from lmqg import TransformersQG

# initialize model
model = TransformersQG(language="ru", model="lmqg/mt5-base-ruquad-qag")

# model prediction
question_answer_pairs = model.generate_qa("Нелишним будет отметить, что, развивая это направление, Д. И. Менделеев, поначалу априорно выдвинув идею о температуре, при которой высота мениска будет нулевой, в мае 1860 года провёл серию опытов.")
  • With transformers
from transformers import pipeline

pipe = pipeline("text2text-generation", "lmqg/mt5-base-ruquad-qag")
output = pipe("Нелишним будет отметить, что, развивая это направление, Д. И. Менделеев, поначалу априорно выдвинув идею о температуре, при которой высота мениска будет нулевой, в мае 1860 года провёл серию опытов.")

Evaluation

Score Type Dataset
QAAlignedF1Score (BERTScore) 74.63 default lmqg/qag_ruquad
QAAlignedF1Score (MoverScore) 54.24 default lmqg/qag_ruquad
QAAlignedPrecision (BERTScore) 73.97 default lmqg/qag_ruquad
QAAlignedPrecision (MoverScore) 53.91 default lmqg/qag_ruquad
QAAlignedRecall (BERTScore) 75.38 default lmqg/qag_ruquad
QAAlignedRecall (MoverScore) 54.65 default lmqg/qag_ruquad

Training hyperparameters

The following hyperparameters were used during fine-tuning:

  • dataset_path: lmqg/qag_ruquad
  • dataset_name: default
  • input_types: ['paragraph']
  • output_types: ['questions_answers']
  • prefix_types: None
  • model: google/mt5-base
  • max_length: 512
  • max_length_output: 256
  • epoch: 12
  • batch: 2
  • lr: 0.0005
  • fp16: False
  • random_seed: 1
  • gradient_accumulation_steps: 32
  • 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
20
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.

Dataset used to train lmqg/mt5-base-ruquad-qag

Evaluation results

  • QAAlignedF1Score-BERTScore (Question & Answer Generation) on lmqg/qag_ruquad
    self-reported
    74.630
  • QAAlignedRecall-BERTScore (Question & Answer Generation) on lmqg/qag_ruquad
    self-reported
    75.380
  • QAAlignedPrecision-BERTScore (Question & Answer Generation) on lmqg/qag_ruquad
    self-reported
    73.970
  • QAAlignedF1Score-MoverScore (Question & Answer Generation) on lmqg/qag_ruquad
    self-reported
    54.240
  • QAAlignedRecall-MoverScore (Question & Answer Generation) on lmqg/qag_ruquad
    self-reported
    54.650
  • QAAlignedPrecision-MoverScore (Question & Answer Generation) on lmqg/qag_ruquad
    self-reported
    53.910