metadata
license: cc-by-4.0
metrics:
- bleu4
- meteor
- rouge-l
- bertscore
- moverscore
language: es
datasets:
- lmqg/qg_esquad
pipeline_tag: text2text-generation
tags:
- question generation
widget:
- text: del <hl> Ministerio de Desarrollo Urbano <hl> , Gobierno de la India.
example_title: Question Generation Example 1
- text: a <hl> noviembre <hl> , que es también la estación lluviosa.
example_title: Question Generation Example 2
- text: >-
como <hl> el gobierno de Abbott <hl> que asumió el cargo el 18 de
septiembre de 2013.
example_title: Question Generation Example 3
model-index:
- name: lmqg/mt5-small-esquad-qg
results:
- task:
name: Text2text Generation
type: text2text-generation
dataset:
name: lmqg/qg_esquad
type: default
args: default
metrics:
- name: BLEU4 (Question Generation)
type: bleu4_question_generation
value: 9.61
- name: ROUGE-L (Question Generation)
type: rouge_l_question_generation
value: 24.62
- name: METEOR (Question Generation)
type: meteor_question_generation
value: 22.71
- name: BERTScore (Question Generation)
type: bertscore_question_generation
value: 84.07
- name: MoverScore (Question Generation)
type: moverscore_question_generation
value: 59.06
- name: BLEU4 (Question & Answer Generation (with Gold Answer))
type: bleu4_question_answer_generation_with_gold_answer
value: 12.77
- name: ROUGE-L (Question & Answer Generation (with Gold Answer))
type: rouge_l_question_answer_generation_with_gold_answer
value: 42.77
- name: METEOR (Question & Answer Generation (with Gold Answer))
type: meteor_question_answer_generation_with_gold_answer
value: 37.58
- name: BERTScore (Question & Answer Generation (with Gold Answer))
type: bertscore_question_answer_generation_with_gold_answer
value: 89.41
- name: MoverScore (Question & Answer Generation (with Gold Answer))
type: moverscore_question_answer_generation_with_gold_answer
value: 63.56
- name: >-
QAAlignedF1Score-BERTScore (Question & Answer Generation (with
Gold Answer)) [Gold Answer]
type: >-
qa_aligned_f1_score_bertscore_question_answer_generation_with_gold_answer_gold_answer
value: 89.43
- name: >-
QAAlignedRecall-BERTScore (Question & Answer Generation (with Gold
Answer)) [Gold Answer]
type: >-
qa_aligned_recall_bertscore_question_answer_generation_with_gold_answer_gold_answer
value: 89.41
- name: >-
QAAlignedPrecision-BERTScore (Question & Answer Generation (with
Gold Answer)) [Gold Answer]
type: >-
qa_aligned_precision_bertscore_question_answer_generation_with_gold_answer_gold_answer
value: 89.44
- name: >-
QAAlignedF1Score-MoverScore (Question & Answer Generation (with
Gold Answer)) [Gold Answer]
type: >-
qa_aligned_f1_score_moverscore_question_answer_generation_with_gold_answer_gold_answer
value: 63.73
- name: >-
QAAlignedRecall-MoverScore (Question & Answer Generation (with
Gold Answer)) [Gold Answer]
type: >-
qa_aligned_recall_moverscore_question_answer_generation_with_gold_answer_gold_answer
value: 63.72
- name: >-
QAAlignedPrecision-MoverScore (Question & Answer Generation (with
Gold Answer)) [Gold Answer]
type: >-
qa_aligned_precision_moverscore_question_answer_generation_with_gold_answer_gold_answer
value: 63.75
- name: BLEU4 (Question & Answer Generation)
type: bleu4_question_answer_generation
value: 1.83
- name: ROUGE-L (Question & Answer Generation)
type: rouge_l_question_answer_generation
value: 15.46
- name: METEOR (Question & Answer Generation)
type: meteor_question_answer_generation
value: 22.22
- name: BERTScore (Question & Answer Generation)
type: bertscore_question_answer_generation
value: 69.78
- name: MoverScore (Question & Answer Generation)
type: moverscore_question_answer_generation
value: 51.8
- name: >-
QAAlignedF1Score-BERTScore (Question & Answer Generation) [Gold
Answer]
type: >-
qa_aligned_f1_score_bertscore_question_answer_generation_gold_answer
value: 79.89
- name: >-
QAAlignedRecall-BERTScore (Question & Answer Generation) [Gold
Answer]
type: qa_aligned_recall_bertscore_question_answer_generation_gold_answer
value: 82.56
- name: >-
QAAlignedPrecision-BERTScore (Question & Answer Generation) [Gold
Answer]
type: >-
qa_aligned_precision_bertscore_question_answer_generation_gold_answer
value: 77.46
- name: >-
QAAlignedF1Score-MoverScore (Question & Answer Generation) [Gold
Answer]
type: >-
qa_aligned_f1_score_moverscore_question_answer_generation_gold_answer
value: 54.82
- name: >-
QAAlignedRecall-MoverScore (Question & Answer Generation) [Gold
Answer]
type: >-
qa_aligned_recall_moverscore_question_answer_generation_gold_answer
value: 56.52
- name: >-
QAAlignedPrecision-MoverScore (Question & Answer Generation) [Gold
Answer]
type: >-
qa_aligned_precision_moverscore_question_answer_generation_gold_answer
value: 53.31
Model Card of lmqg/mt5-small-esquad-qg
This model is fine-tuned version of google/mt5-small for question generation task on the lmqg/qg_esquad (dataset_name: default) via lmqg.
Overview
- Language model: google/mt5-small
- Language: es
- Training data: lmqg/qg_esquad (default)
- 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="es", model="lmqg/mt5-small-esquad-qg")
# model prediction
questions = model.generate_q(list_context="a noviembre , que es también la estación lluviosa.", list_answer="noviembre")
- With
transformers
from transformers import pipeline
pipe = pipeline("text2text-generation", "lmqg/mt5-small-esquad-qg")
output = pipe("del <hl> Ministerio de Desarrollo Urbano <hl> , Gobierno de la India.")
Evaluation
- Metric (Question Generation): raw metric file
| Score | Type | Dataset | |
|---|---|---|---|
| BERTScore | 84.07 | default | lmqg/qg_esquad |
| Bleu_1 | 26.03 | default | lmqg/qg_esquad |
| Bleu_2 | 17.75 | default | lmqg/qg_esquad |
| Bleu_3 | 12.88 | default | lmqg/qg_esquad |
| Bleu_4 | 9.61 | default | lmqg/qg_esquad |
| METEOR | 22.71 | default | lmqg/qg_esquad |
| MoverScore | 59.06 | default | lmqg/qg_esquad |
| ROUGE_L | 24.62 | default | lmqg/qg_esquad |
- Metric (Question & Answer Generation, Reference Answer): Each question is generated from the gold answer. raw metric file
| Score | Type | Dataset | |
|---|---|---|---|
| BERTScore | 89.41 | default | lmqg/qg_esquad |
| Bleu_1 | 39.84 | default | lmqg/qg_esquad |
| Bleu_2 | 26.59 | default | lmqg/qg_esquad |
| Bleu_3 | 18.28 | default | lmqg/qg_esquad |
| Bleu_4 | 12.77 | default | lmqg/qg_esquad |
| METEOR | 37.58 | default | lmqg/qg_esquad |
| MoverScore | 63.56 | default | lmqg/qg_esquad |
| QAAlignedF1Score (BERTScore) | 89.43 | default | lmqg/qg_esquad |
| QAAlignedF1Score (MoverScore) | 63.73 | default | lmqg/qg_esquad |
| QAAlignedPrecision (BERTScore) | 89.44 | default | lmqg/qg_esquad |
| QAAlignedPrecision (MoverScore) | 63.75 | default | lmqg/qg_esquad |
| QAAlignedRecall (BERTScore) | 89.41 | default | lmqg/qg_esquad |
| QAAlignedRecall (MoverScore) | 63.72 | default | lmqg/qg_esquad |
| ROUGE_L | 42.77 | default | lmqg/qg_esquad |
- Metric (Question & Answer Generation, Pipeline Approach): Each question is generated on the answer generated by
lmqg/mt5-small-esquad-ae. raw metric file
| Score | Type | Dataset | |
|---|---|---|---|
| BERTScore | 69.78 | default | lmqg/qg_esquad |
| Bleu_1 | 11.1 | default | lmqg/qg_esquad |
| Bleu_2 | 5.5 | default | lmqg/qg_esquad |
| Bleu_3 | 3 | default | lmqg/qg_esquad |
| Bleu_4 | 1.83 | default | lmqg/qg_esquad |
| METEOR | 22.22 | default | lmqg/qg_esquad |
| MoverScore | 51.8 | default | lmqg/qg_esquad |
| QAAlignedF1Score (BERTScore) | 79.89 | default | lmqg/qg_esquad |
| QAAlignedF1Score (MoverScore) | 54.82 | default | lmqg/qg_esquad |
| QAAlignedPrecision (BERTScore) | 77.46 | default | lmqg/qg_esquad |
| QAAlignedPrecision (MoverScore) | 53.31 | default | lmqg/qg_esquad |
| QAAlignedRecall (BERTScore) | 82.56 | default | lmqg/qg_esquad |
| QAAlignedRecall (MoverScore) | 56.52 | default | lmqg/qg_esquad |
| ROUGE_L | 15.46 | default | lmqg/qg_esquad |
Training hyperparameters
The following hyperparameters were used during fine-tuning:
- dataset_path: lmqg/qg_esquad
- dataset_name: default
- input_types: ['paragraph_answer']
- output_types: ['question']
- prefix_types: None
- model: google/mt5-small
- max_length: 512
- max_length_output: 32
- epoch: 16
- batch: 64
- lr: 0.0005
- fp16: False
- random_seed: 1
- gradient_accumulation_steps: 1
- 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",
}