metadata
license: cc-by-4.0
metrics:
- bleu4
- meteor
- rouge-l
- bertscore
- moverscore
language: it
datasets:
- lmqg/qg_itquad
pipeline_tag: text2text-generation
tags:
- question generation
widget:
- text: >-
<hl> Dopo il 1971 <hl> , l' OPEC ha tardato ad adeguare i prezzi per
riflettere tale deprezzamento.
example_title: Question Generation Example 1
- text: >-
L' individuazione del petrolio e lo sviluppo di nuovi giacimenti
richiedeva in genere <hl> da cinque a dieci anni <hl> prima di una
produzione significativa.
example_title: Question Generation Example 2
- text: il <hl> Giappone <hl> è stato il paese più dipendente dal petrolio arabo.
example_title: Question Generation Example 3
model-index:
- name: lmqg/mt5-small-itquad-qg
results:
- task:
name: Text2text Generation
type: text2text-generation
dataset:
name: lmqg/qg_itquad
type: default
args: default
metrics:
- name: BLEU4 (Question Generation)
type: bleu4_question_generation
value: 7.37
- name: ROUGE-L (Question Generation)
type: rouge_l_question_generation
value: 21.93
- name: METEOR (Question Generation)
type: meteor_question_generation
value: 17.57
- name: BERTScore (Question Generation)
type: bertscore_question_generation
value: 80.8
- name: MoverScore (Question Generation)
type: moverscore_question_generation
value: 56.79
- name: BLEU4 (Question & Answer Generation (with Gold Answer))
type: bleu4_question_answer_generation_with_gold_answer
value: 15.44
- name: ROUGE-L (Question & Answer Generation (with Gold Answer))
type: rouge_l_question_answer_generation_with_gold_answer
value: 40.08
- name: METEOR (Question & Answer Generation (with Gold Answer))
type: meteor_question_answer_generation_with_gold_answer
value: 34.31
- name: BERTScore (Question & Answer Generation (with Gold Answer))
type: bertscore_question_answer_generation_with_gold_answer
value: 86.62
- name: MoverScore (Question & Answer Generation (with Gold Answer))
type: moverscore_question_answer_generation_with_gold_answer
value: 60.68
- 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: 87.66
- 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: 87.57
- 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: 87.76
- 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: 61.6
- 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: 61.48
- 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: 61.73
- name: BLEU4 (Question & Answer Generation)
type: bleu4_question_answer_generation
value: 3.48
- name: ROUGE-L (Question & Answer Generation)
type: rouge_l_question_answer_generation
value: 23.31
- name: METEOR (Question & Answer Generation)
type: meteor_question_answer_generation
value: 23.95
- name: BERTScore (Question & Answer Generation)
type: bertscore_question_answer_generation
value: 77.23
- name: MoverScore (Question & Answer Generation)
type: moverscore_question_answer_generation
value: 54.66
- name: >-
QAAlignedF1Score-BERTScore (Question & Answer Generation) [Gold
Answer]
type: >-
qa_aligned_f1_score_bertscore_question_answer_generation_gold_answer
value: 81.63
- name: >-
QAAlignedRecall-BERTScore (Question & Answer Generation) [Gold
Answer]
type: qa_aligned_recall_bertscore_question_answer_generation_gold_answer
value: 82.28
- name: >-
QAAlignedPrecision-BERTScore (Question & Answer Generation) [Gold
Answer]
type: >-
qa_aligned_precision_bertscore_question_answer_generation_gold_answer
value: 81.04
- name: >-
QAAlignedF1Score-MoverScore (Question & Answer Generation) [Gold
Answer]
type: >-
qa_aligned_f1_score_moverscore_question_answer_generation_gold_answer
value: 55.85
- name: >-
QAAlignedRecall-MoverScore (Question & Answer Generation) [Gold
Answer]
type: >-
qa_aligned_recall_moverscore_question_answer_generation_gold_answer
value: 56.14
- name: >-
QAAlignedPrecision-MoverScore (Question & Answer Generation) [Gold
Answer]
type: >-
qa_aligned_precision_moverscore_question_answer_generation_gold_answer
value: 55.6
Model Card of lmqg/mt5-small-itquad-qg
This model is fine-tuned version of google/mt5-small for question generation task on the lmqg/qg_itquad (dataset_name: default) via lmqg.
Overview
- Language model: google/mt5-small
- Language: it
- Training data: lmqg/qg_itquad (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="it", model="lmqg/mt5-small-itquad-qg")
# model prediction
questions = model.generate_q(list_context="Dopo il 1971 , l' OPEC ha tardato ad adeguare i prezzi per riflettere tale deprezzamento.", list_answer="Dopo il 1971")
- With
transformers
from transformers import pipeline
pipe = pipeline("text2text-generation", "lmqg/mt5-small-itquad-qg")
output = pipe("<hl> Dopo il 1971 <hl> , l' OPEC ha tardato ad adeguare i prezzi per riflettere tale deprezzamento.")
Evaluation
- Metric (Question Generation): raw metric file
| Score | Type | Dataset | |
|---|---|---|---|
| BERTScore | 80.8 | default | lmqg/qg_itquad |
| Bleu_1 | 22.78 | default | lmqg/qg_itquad |
| Bleu_2 | 14.93 | default | lmqg/qg_itquad |
| Bleu_3 | 10.34 | default | lmqg/qg_itquad |
| Bleu_4 | 7.37 | default | lmqg/qg_itquad |
| METEOR | 17.57 | default | lmqg/qg_itquad |
| MoverScore | 56.79 | default | lmqg/qg_itquad |
| ROUGE_L | 21.93 | default | lmqg/qg_itquad |
- Metric (Question & Answer Generation, Reference Answer): Each question is generated from the gold answer. raw metric file
| Score | Type | Dataset | |
|---|---|---|---|
| BERTScore | 86.62 | default | lmqg/qg_itquad |
| Bleu_1 | 40.5 | default | lmqg/qg_itquad |
| Bleu_2 | 28.64 | default | lmqg/qg_itquad |
| Bleu_3 | 20.78 | default | lmqg/qg_itquad |
| Bleu_4 | 15.44 | default | lmqg/qg_itquad |
| METEOR | 34.31 | default | lmqg/qg_itquad |
| MoverScore | 60.68 | default | lmqg/qg_itquad |
| QAAlignedF1Score (BERTScore) | 87.66 | default | lmqg/qg_itquad |
| QAAlignedF1Score (MoverScore) | 61.6 | default | lmqg/qg_itquad |
| QAAlignedPrecision (BERTScore) | 87.76 | default | lmqg/qg_itquad |
| QAAlignedPrecision (MoverScore) | 61.73 | default | lmqg/qg_itquad |
| QAAlignedRecall (BERTScore) | 87.57 | default | lmqg/qg_itquad |
| QAAlignedRecall (MoverScore) | 61.48 | default | lmqg/qg_itquad |
| ROUGE_L | 40.08 | default | lmqg/qg_itquad |
- Metric (Question & Answer Generation, Pipeline Approach): Each question is generated on the answer generated by
lmqg/mt5-small-itquad-ae. raw metric file
| Score | Type | Dataset | |
|---|---|---|---|
| BERTScore | 77.23 | default | lmqg/qg_itquad |
| Bleu_1 | 23.77 | default | lmqg/qg_itquad |
| Bleu_2 | 13.25 | default | lmqg/qg_itquad |
| Bleu_3 | 6.48 | default | lmqg/qg_itquad |
| Bleu_4 | 3.48 | default | lmqg/qg_itquad |
| METEOR | 23.95 | default | lmqg/qg_itquad |
| MoverScore | 54.66 | default | lmqg/qg_itquad |
| QAAlignedF1Score (BERTScore) | 81.63 | default | lmqg/qg_itquad |
| QAAlignedF1Score (MoverScore) | 55.85 | default | lmqg/qg_itquad |
| QAAlignedPrecision (BERTScore) | 81.04 | default | lmqg/qg_itquad |
| QAAlignedPrecision (MoverScore) | 55.6 | default | lmqg/qg_itquad |
| QAAlignedRecall (BERTScore) | 82.28 | default | lmqg/qg_itquad |
| QAAlignedRecall (MoverScore) | 56.14 | default | lmqg/qg_itquad |
| ROUGE_L | 23.31 | default | lmqg/qg_itquad |
Training hyperparameters
The following hyperparameters were used during fine-tuning:
- dataset_path: lmqg/qg_itquad
- 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: 15
- batch: 16
- lr: 0.0005
- fp16: False
- random_seed: 1
- gradient_accumulation_steps: 4
- label_smoothing: 0.0
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",
}