Transformer Models for Brazilian Portuguese Question Generation: An Experimental Study

Unlike tasks such as translation or summarization, generating meaningful questions necessitates a profound understanding of context, semantics, and syntax. This complexity arises from the need to not only comprehend the given text comprehensively but also infer information gaps, identify relevant en...

Full description

Saved in:
Bibliographic Details
Main Authors: Julia da Rocha Junqueira, Ulisses Brisolara Corrêa, Larissa Freitas
Format: Article
Language:English
Published: LibraryPress@UF 2024-05-01
Series:Proceedings of the International Florida Artificial Intelligence Research Society Conference
Subjects:
Online Access:https://journals.flvc.org/FLAIRS/article/view/135334
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849736822128640000
author Julia da Rocha Junqueira
Ulisses Brisolara Corrêa
Larissa Freitas
author_facet Julia da Rocha Junqueira
Ulisses Brisolara Corrêa
Larissa Freitas
author_sort Julia da Rocha Junqueira
collection DOAJ
description Unlike tasks such as translation or summarization, generating meaningful questions necessitates a profound understanding of context, semantics, and syntax. This complexity arises from the need to not only comprehend the given text comprehensively but also infer information gaps, identify relevant entities, and construct syntactically and semantically correct interrogative sentences. We address this challenge by proposing an experimental fine-tuning approach for encoder-decoder models (T5, FLAN-T5, and BART-PT) tailored explicitly for Brazilian Portuguese question generation. Our study involves fine-tuning these models on the SQUAD-v1.1 dataset and subsequent evaluation, also on SQUAD-v1.1. Through our experimental endeavors, BART returned a higher result in all the ROUGE metrics, as ROUGE-1 0.46, ROUGE-2 0.24, and ROUGE-L 0.43, suggesting a higher lexical similarity in the questions generated, and it is comparable to the results of the question generation task for the English language. We explored how these advancements can significantly enhance the precision and quality of the question generation task in Brazilian Portuguese, bridging the gap between training data and the intricacies of interrogative sentence construction.
format Article
id doaj-art-5896649fb0274cd7a245feb2d5c4a65f
institution DOAJ
issn 2334-0754
2334-0762
language English
publishDate 2024-05-01
publisher LibraryPress@UF
record_format Article
series Proceedings of the International Florida Artificial Intelligence Research Society Conference
spelling doaj-art-5896649fb0274cd7a245feb2d5c4a65f2025-08-20T03:07:10ZengLibraryPress@UFProceedings of the International Florida Artificial Intelligence Research Society Conference2334-07542334-07622024-05-013710.32473/flairs.37.1.13533471707Transformer Models for Brazilian Portuguese Question Generation: An Experimental StudyJulia da Rocha Junqueira0https://orcid.org/0009-0008-6600-3163Ulisses Brisolara Corrêa1Larissa FreitasUFPELUFPELUnlike tasks such as translation or summarization, generating meaningful questions necessitates a profound understanding of context, semantics, and syntax. This complexity arises from the need to not only comprehend the given text comprehensively but also infer information gaps, identify relevant entities, and construct syntactically and semantically correct interrogative sentences. We address this challenge by proposing an experimental fine-tuning approach for encoder-decoder models (T5, FLAN-T5, and BART-PT) tailored explicitly for Brazilian Portuguese question generation. Our study involves fine-tuning these models on the SQUAD-v1.1 dataset and subsequent evaluation, also on SQUAD-v1.1. Through our experimental endeavors, BART returned a higher result in all the ROUGE metrics, as ROUGE-1 0.46, ROUGE-2 0.24, and ROUGE-L 0.43, suggesting a higher lexical similarity in the questions generated, and it is comparable to the results of the question generation task for the English language. We explored how these advancements can significantly enhance the precision and quality of the question generation task in Brazilian Portuguese, bridging the gap between training data and the intricacies of interrogative sentence construction.https://journals.flvc.org/FLAIRS/article/view/135334natural language processingtransformersparallel multi-head attention mechanismsquestion generationencoder-decoder modelsbrazilian portuguesesquad-v1.1 datasetexperimental fine-tuning
spellingShingle Julia da Rocha Junqueira
Ulisses Brisolara Corrêa
Larissa Freitas
Transformer Models for Brazilian Portuguese Question Generation: An Experimental Study
Proceedings of the International Florida Artificial Intelligence Research Society Conference
natural language processing
transformers
parallel multi-head attention mechanisms
question generation
encoder-decoder models
brazilian portuguese
squad-v1.1 dataset
experimental fine-tuning
title Transformer Models for Brazilian Portuguese Question Generation: An Experimental Study
title_full Transformer Models for Brazilian Portuguese Question Generation: An Experimental Study
title_fullStr Transformer Models for Brazilian Portuguese Question Generation: An Experimental Study
title_full_unstemmed Transformer Models for Brazilian Portuguese Question Generation: An Experimental Study
title_short Transformer Models for Brazilian Portuguese Question Generation: An Experimental Study
title_sort transformer models for brazilian portuguese question generation an experimental study
topic natural language processing
transformers
parallel multi-head attention mechanisms
question generation
encoder-decoder models
brazilian portuguese
squad-v1.1 dataset
experimental fine-tuning
url https://journals.flvc.org/FLAIRS/article/view/135334
work_keys_str_mv AT juliadarochajunqueira transformermodelsforbrazilianportuguesequestiongenerationanexperimentalstudy
AT ulissesbrisolaracorrea transformermodelsforbrazilianportuguesequestiongenerationanexperimentalstudy
AT larissafreitas transformermodelsforbrazilianportuguesequestiongenerationanexperimentalstudy