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-small-subjqa-vanilla-movies
results:
- task:
name: Text2text Generation
type: text2text-generation
dataset:
name: lmqg/qg_subjqa
type: movies
args: movies
metrics:
- name: BLEU4
type: bleu4
value: 0
- name: ROUGE-L
type: rouge-l
value: 0.28
- name: METEOR
type: meteor
value: 0.22
- name: BERTScore
type: bertscore
value: 4.78
- name: MoverScore
type: moverscore
value: 49.11
Model Card of lmqg/t5-small-subjqa-vanilla-movies
This model is fine-tuned version of t5-small for question generation task on the lmqg/qg_subjqa (dataset_name: movies) via lmqg
.
Overview
- Language model: t5-small
- Language: en
- Training data: lmqg/qg_subjqa (movies)
- 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-small-subjqa-vanilla-movies")
# 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-small-subjqa-vanilla-movies")
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 | 4.78 | movies | lmqg/qg_subjqa |
Bleu_1 | 0.17 | movies | lmqg/qg_subjqa |
Bleu_2 | 0 | movies | lmqg/qg_subjqa |
Bleu_3 | 0 | movies | lmqg/qg_subjqa |
Bleu_4 | 0 | movies | lmqg/qg_subjqa |
METEOR | 0.22 | movies | lmqg/qg_subjqa |
MoverScore | 49.11 | movies | lmqg/qg_subjqa |
ROUGE_L | 0.28 | movies | lmqg/qg_subjqa |
Training hyperparameters
The following hyperparameters were used during fine-tuning:
- dataset_path: lmqg/qg_subjqa
- dataset_name: movies
- input_types: ['paragraph_answer']
- output_types: ['question']
- prefix_types: ['qg']
- model: t5-small
- max_length: 512
- max_length_output: 32
- epoch: 1
- batch: 32
- lr: 0.0001
- fp16: False
- random_seed: 1
- gradient_accumulation_steps: 2
- 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",
}