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: >-
      <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: >-
      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: >-
      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/bart-large-subjqa-grocery-qg
    results:
      - task:
          name: Text2text Generation
          type: text2text-generation
        dataset:
          name: lmqg/qg_subjqa
          type: grocery
          args: grocery
        metrics:
          - name: BLEU4 (Question Generation)
            type: bleu4_question_generation
            value: 1.93
          - name: ROUGE-L (Question Generation)
            type: rouge_l_question_generation
            value: 24.28
          - name: METEOR (Question Generation)
            type: meteor_question_generation
            value: 20.42
          - name: BERTScore (Question Generation)
            type: bertscore_question_generation
            value: 94.1
          - name: MoverScore (Question Generation)
            type: moverscore_question_generation
            value: 65.79

Model Card of `lmqg/bart-large-subjqa-grocery-qg`

This model is fine-tuned version of lmqg/bart-large-squad for question generation task on the lmqg/qg_subjqa (dataset_name: grocery) via lmqg.

Overview

Language model: lmqg/bart-large-squad
Language: en
Training data: lmqg/qg_subjqa (grocery)
Online Demo: https://autoqg.net/
Repository: https://github.com/asahi417/lm-question-generation
Paper: https://arxiv.org/abs/2210.03992

Usage

With lmqg

from lmqg import TransformersQG

# initialize model
model = TransformersQG(language="en", model="lmqg/bart-large-subjqa-grocery-qg")

# model prediction
questions = model.generate_q(list_context="William Turner was an English painter who specialised in watercolour landscapes", list_answer="William Turner")

With transformers

from transformers import pipeline

pipe = pipeline("text2text-generation", "lmqg/bart-large-subjqa-grocery-qg")
output = pipe("<hl> Beyonce <hl> further expanded her acting career, starring as blues singer Etta James in the 2008 musical biopic, Cadillac Records.")

Evaluation

Metric (Question Generation): raw metric file

	Score	Type	Dataset
BERTScore	94.1	grocery	lmqg/qg_subjqa
Bleu_1	23.2	grocery	lmqg/qg_subjqa
Bleu_2	15.22	grocery	lmqg/qg_subjqa
Bleu_3	4.85	grocery	lmqg/qg_subjqa
Bleu_4	1.93	grocery	lmqg/qg_subjqa
METEOR	20.42	grocery	lmqg/qg_subjqa
MoverScore	65.79	grocery	lmqg/qg_subjqa
ROUGE_L	24.28	grocery	lmqg/qg_subjqa

Training hyperparameters

The following hyperparameters were used during fine-tuning:

dataset_path: lmqg/qg_subjqa
dataset_name: grocery
input_types: ['paragraph_answer']
output_types: ['question']
prefix_types: None
model: lmqg/bart-large-squad
max_length: 512
max_length_output: 32
epoch: 4
batch: 8
lr: 5e-05
fp16: False
random_seed: 1
gradient_accumulation_steps: 32
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",
}