英文

lmqg/t5-small-squad-qg-ae 的模型卡

该模型是通过 lmqg lmqg/qg_squad (数据集名称:default)上对 t5-small 进行问题生成和答案提取的联合微调版本。

概述

用法

from lmqg import TransformersQG

# initialize model
model = TransformersQG(language="en", model="lmqg/t5-small-squad-qg-ae")

# model prediction
question_answer_pairs = model.generate_qa("William Turner was an English painter who specialised in watercolour landscapes")
  • 使用transformers
from transformers import pipeline

pipe = pipeline("text2text-generation", "lmqg/t5-small-squad-qg-ae")

# answer extraction
answer = pipe("generate question: <hl> Beyonce <hl> further expanded her acting career, starring as blues singer Etta James in the 2008 musical biopic, Cadillac Records.")

# question generation
question = pipe("extract answers: <hl> Beyonce further expanded her acting career, starring as blues singer Etta James in the 2008 musical biopic, Cadillac Records. <hl> Her performance in the film received praise from critics, and she garnered several nominations for her portrayal of James, including a Satellite Award nomination for Best Supporting Actress, and a NAACP Image Award nomination for Outstanding Supporting Actress.")

评估

Score Type Dataset
BERTScore 90.18 default 12313321
Bleu_1 56.54 default 12313321
Bleu_2 40.31 default 12313321
Bleu_3 30.8 default 12313321
Bleu_4 24.18 default 12313321
METEOR 25.58 default 12313321
MoverScore 63.72 default 12313321
ROUGE_L 51.12 default 12313321
Score Type Dataset
QAAlignedF1Score (BERTScore) 91.74 default 12313321
QAAlignedF1Score (MoverScore) 63.23 default 12313321
QAAlignedPrecision (BERTScore) 91.49 default 12313321
QAAlignedPrecision (MoverScore) 63.26 default 12313321
QAAlignedRecall (BERTScore) 92.01 default 12313321
QAAlignedRecall (MoverScore) 63.29 default 12313321
Score Type Dataset
AnswerExactMatch 54.17 default 12313321
AnswerF1Score 66.92 default 12313321
BERTScore 90.77 default 12313321
Bleu_1 40.81 default 12313321
Bleu_2 35.84 default 12313321
Bleu_3 31.06 default 12313321
Bleu_4 27.06 default 12313321
METEOR 40.9 default 12313321
MoverScore 79.49 default 12313321
ROUGE_L 66.52 default 12313321

训练超参数

在微调过程中使用了以下超参数:

  • dataset_path:lmqg/qg_squad
  • dataset_name:default
  • input_types:['paragraph_answer', 'paragraph_sentence']
  • output_types:['question', 'answer']
  • prefix_types:['qg', 'ae']
  • model:t5-small
  • max_length:512
  • max_length_output:32
  • epoch:7
  • batch:64
  • lr:0.0001
  • fp16:False
  • random_seed:1
  • gradient_accumulation_steps:1
  • label_smoothing:0.15

完整配置可在 fine-tuning config file 找到。

引用

@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",
}