README.md

metadata

license: cc-by-4.0
metrics:
  - bleu4
  - meteor
  - rouge-l
  - bertscore
  - moverscore
language: en
datasets:
  - lmqg/qg_subjqa
pipeline_tag: text2text-generation
tags:
  - question generation
widget:
  - text: >-
      generate question: <hl> Beyonce <hl> further expanded her acting career,
      starring as blues singer Etta James in the 2008 musical biopic, Cadillac
      Records.
    example_title: Question Generation Example 1
  - text: >-
      generate question: Beyonce further expanded her acting career, starring as
      blues singer <hl> Etta James <hl> in the 2008 musical biopic, Cadillac
      Records.
    example_title: Question Generation Example 2
  - text: >-
      generate question: Beyonce further expanded her acting career, starring as
      blues singer Etta James in the 2008 musical biopic,  <hl> Cadillac Records
      <hl> .
    example_title: Question Generation Example 3
model-index:
  - name: lmqg/t5-base-subjqa-books
    results:
      - task:
          name: Text2text Generation
          type: text2text-generation
        dataset:
          name: lmqg/qg_subjqa
          type: books
          args: books
        metrics:
          - name: BLEU4
            type: bleu4
            value: 0.000002600973149435955
          - name: ROUGE-L
            type: rouge-l
            value: 0.22951859052862766
          - name: METEOR
            type: meteor
            value: 0.21203557376943663
          - name: BERTScore
            type: bertscore
            value: 0.9331581589439153
          - name: MoverScore
            type: moverscore
            value: 0.6314041710040545
      - task:
          name: Text2text Generation
          type: text2text-generation
        dataset:
          name: lmqg/qg_squad
          type: default
          args: default
        metrics:
          - name: BLEU4
            type: bleu4
            value: 0.2087191069506097
          - name: ROUGE-L
            type: rouge-l
            value: 0.4824194822687923
          - name: METEOR
            type: meteor
            value: 0.22369289060703182
          - name: BERTScore
            type: bertscore
            value: 0.9063421096238328
          - name: MoverScore
            type: moverscore
            value: 0.6228301030244887

Language Models Fine-tuning on Question Generation: lmqg/t5-base-subjqa-books

This model is fine-tuned version of lmqg/t5-base-squad for question generation task on the lmqg/qg_subjqa (dataset_name: books). This model is continuously fine-tuned with lmqg/t5-base-squad.

Overview

• Language model: lmqg/t5-base-squad
• Language: en
• Training data: lmqg/qg_subjqa (books)
• Online Demo: https://autoqg.net/
• Repository: https://github.com/asahi417/lm-question-generation
• Paper: TBA

Usage

from transformers import pipeline

model_path = 'lmqg/t5-base-subjqa-books'
pipe = pipeline("text2text-generation", model_path)

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

Evaluation Metrics

Metrics

Dataset	Type	BLEU4	ROUGE-L	METEOR	BERTScore	MoverScore	Link
lmqg/qg_subjqa	books	2.600973149435955e-06	0.22951859052862766	0.21203557376943663	0.9331581589439153	0.6314041710040545	link

Out-of-domain Metrics

Dataset	Type	BLEU4	ROUGE-L	METEOR	BERTScore	MoverScore	Link
lmqg/qg_squad	default	0.2087191069506097	0.4824194822687923	0.22369289060703182	0.9063421096238328	0.6228301030244887	link

Training hyperparameters

The following hyperparameters were used during fine-tuning:

• dataset_path: lmqg/qg_subjqa
• dataset_name: books
• input_types: ['paragraph_answer']
• output_types: ['question']
• prefix_types: ['qg']
• model: lmqg/t5-base-squad
• max_length: 512
• max_length_output: 32
• epoch: 3
• batch: 16
• lr: 0.0001
• 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

TBA