metadata

license: cc-by-4.0
metrics:
  - bleu4
  - meteor
  - rouge-l
  - bertscore
  - moverscore
language: en
datasets:
  - lmqg/qg_squadshifts
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-large-squadshifts-amazon
    results:
      - task:
          name: Text2text Generation
          type: text2text-generation
        dataset:
          name: lmqg/qg_squadshifts
          type: amazon
          args: amazon
        metrics:
          - name: BLEU4
            type: bleu4
            value: 10.42
          - name: ROUGE-L
            type: rouge-l
            value: 29.51
          - name: METEOR
            type: meteor
            value: 24.39
          - name: BERTScore
            type: bertscore
            value: 92.65
          - name: MoverScore
            type: moverscore
            value: 63.71

Model Card of `lmqg/t5-large-squadshifts-amazon`

This model is fine-tuned version of lmqg/t5-large-squad for question generation task on the lmqg/qg_squadshifts (dataset_name: amazon) via lmqg. This model is continuously fine-tuned with lmqg/t5-large-squad.

Overview

Language model: lmqg/t5-large-squad
Language: en
Training data: lmqg/qg_squadshifts (amazon)
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/t5-large-squadshifts-amazon")

# 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/t5-large-squadshifts-amazon")
output = 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

Metric (Question Generation): raw metric file

	Score	Type	Dataset
BERTScore	92.65	amazon	lmqg/qg_squadshifts
Bleu_1	29.57	amazon	lmqg/qg_squadshifts
Bleu_2	20.46	amazon	lmqg/qg_squadshifts
Bleu_3	14.4	amazon	lmqg/qg_squadshifts
Bleu_4	10.42	amazon	lmqg/qg_squadshifts
METEOR	24.39	amazon	lmqg/qg_squadshifts
MoverScore	63.71	amazon	lmqg/qg_squadshifts
ROUGE_L	29.51	amazon	lmqg/qg_squadshifts

Training hyperparameters

The following hyperparameters were used during fine-tuning:

dataset_path: lmqg/qg_squadshifts
dataset_name: amazon
input_types: ['paragraph_answer']
output_types: ['question']
prefix_types: ['qg']
model: lmqg/t5-large-squad
max_length: 512
max_length_output: 32
epoch: 2
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

@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",
}