Edit model card

Model Card of vocabtrimmer/mt5-base-trimmed-ko-15000-koquad-qg

This model is fine-tuned version of vocabtrimmer/mt5-base-trimmed-ko-15000 for question generation task on the lmqg/qg_koquad (dataset_name: default) via lmqg.

Overview

Usage

from lmqg import TransformersQG

# initialize model
model = TransformersQG(language="ko", model="vocabtrimmer/mt5-base-trimmed-ko-15000-koquad-qg")

# model prediction
questions = model.generate_q(list_context="1990년 영화 《 남부군 》에서 단역으로 영화배우 첫 데뷔에 이어 같은 해 KBS 드라마 《지구인》에서 단역으로 출연하였고 이듬해 MBC 《여명의 눈동자》를 통해 단역으로 출연하였다.", list_answer="남부군")
  • With transformers
from transformers import pipeline

pipe = pipeline("text2text-generation", "vocabtrimmer/mt5-base-trimmed-ko-15000-koquad-qg")
output = pipe("1990년 영화 《 <hl> 남부군 <hl> 》에서 단역으로 영화배우 첫 데뷔에 이어 같은 해 KBS 드라마 《지구인》에서 단역으로 출연하였고 이듬해 MBC 《여명의 눈동자》를 통해 단역으로 출연하였다.")

Evaluation

Score Type Dataset
BERTScore 83.92 default lmqg/qg_koquad
Bleu_1 27.39 default lmqg/qg_koquad
Bleu_2 20.25 default lmqg/qg_koquad
Bleu_3 15.29 default lmqg/qg_koquad
Bleu_4 11.7 default lmqg/qg_koquad
METEOR 28.76 default lmqg/qg_koquad
MoverScore 82.94 default lmqg/qg_koquad
ROUGE_L 27.43 default lmqg/qg_koquad

Training hyperparameters

The following hyperparameters were used during fine-tuning:

  • dataset_path: lmqg/qg_koquad
  • dataset_name: default
  • input_types: paragraph_answer
  • output_types: question
  • prefix_types: None
  • model: vocabtrimmer/mt5-base-trimmed-ko-15000
  • 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: 0.15

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
1

Dataset used to train research-backup/mt5-base-trimmed-ko-15000-koquad-qg

Evaluation results