asahi417's picture
model update
ba257d9
|
raw
history blame
7.89 kB
metadata
license: cc-by-4.0
metrics:
  - bleu4
  - meteor
  - rouge-l
  - bertscore
  - moverscore
language: en
datasets:
  - lmqg/qg_dequad
pipeline_tag: text2text-generation
tags:
  - question generation
  - answer extraction
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
  - text: >-
      <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.
    example_title: Answer Extraction Example 1
  - text: >-
      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. <hl>
    example_title: Answer Extraction Example 2
model-index:
  - name: lmqg/mt5-small-dequad-multitask
    results:
      - task:
          name: Text2text Generation
          type: text2text-generation
        dataset:
          name: lmqg/qg_dequad
          type: default
          args: default
        metrics:
          - name: BLEU4
            type: bleu4
            value: 0.008153318257935705
          - name: ROUGE-L
            type: rouge-l
            value: 0.10153326763371277
          - name: METEOR
            type: meteor
            value: 0.12181097136639749
          - name: BERTScore
            type: bertscore
            value: 0.8038890473051649
          - name: MoverScore
            type: moverscore
            value: 0.551016955735025
          - name: QAAlignedF1Score (BERTScore)
            type: qa_aligned_f1_score_bertscore
            value: 0.799873268285167
          - name: QAAlignedRecall (BERTScore)
            type: qa_aligned_recall_bertscore
            value: 0.812945931926931
          - name: QAAlignedPrecision (BERTScore)
            type: qa_aligned_precision_bertscore
            value: 0.7878875412489514
          - name: QAAlignedF1Score (MoverScore)
            type: qa_aligned_f1_score_moverscore
            value: 0.5388739369566669
          - name: QAAlignedRecall (MoverScore)
            type: qa_aligned_recall_moverscore
            value: 0.5426169060178441
          - name: QAAlignedPrecision (MoverScore)
            type: qa_aligned_precision_moverscore
            value: 0.535616846379365

Model Card of lmqg/mt5-small-dequad-multitask

This model is fine-tuned version of google/mt5-small for question generation task on the lmqg/qg_dequad (dataset_name: default) via lmqg. This model is fine-tuned on the answer extraction task as well as the question generation.

Please cite our paper if you use the model (https://arxiv.org/abs/2210.03992).


@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",
}

Overview

Usage


from lmqg import TransformersQG
# initialize model
model = TransformersQG(language='en', model='lmqg/mt5-small-dequad-multitask')
# model prediction
question_answer = model.generate_qa("William Turner was an English painter who specialised in watercolour landscapes")
  • With transformers

from transformers import pipeline
# initialize model
pipe = pipeline("text2text-generation", 'lmqg/mt5-small-dequad-multitask')
# answer extraction
answer = 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.')
# question generation
question = pipe('generate question: <hl> Beyonce <hl> further expanded her acting career, starring as blues singer Etta James in the 2008 musical biopic, Cadillac Records.')

Evaluation Metrics

Metrics

Dataset Type BLEU4 ROUGE-L METEOR BERTScore MoverScore Link
lmqg/qg_dequad default 0.008 0.102 0.122 0.804 0.551 link

Metrics (QAG)

Dataset Type QA Aligned F1 Score (BERTScore) QA Aligned F1 Score (MoverScore) Link
lmqg/qg_dequad default 0.8 0.539 link

Training hyperparameters

The following hyperparameters were used during fine-tuning:

  • dataset_path: lmqg/qg_dequad
  • 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: 15
  • 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",
}