Please use this identifier to cite or link to this item:
http://hdl.handle.net/1843/57494
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.creator | Thiago Castro Ferreira | pt_BR |
dc.creator | João Victor de Pinho Costa | pt_BR |
dc.creator | Daniel Hasan Dalip | pt_BR |
dc.creator | Celso França | pt_BR |
dc.creator | Marcos André Gonçalves | pt_BR |
dc.creator | Rodrigo Bastos Fóscolo | pt_BR |
dc.creator | Adriana Silvina Pagano | pt_BR |
dc.creator | Isabela Rigotto | pt_BR |
dc.creator | Vitoria Portella | pt_BR |
dc.creator | Gabriel Frota | pt_BR |
dc.creator | Ana Luisa A. R. Guimarães | pt_BR |
dc.creator | Adalberto Penna | pt_BR |
dc.creator | Isabela Lee | pt_BR |
dc.creator | Tayane A. Soares | pt_BR |
dc.creator | Sophia Rolim | pt_BR |
dc.creator | Rossana Cunha | pt_BR |
dc.creator | Ariel Santos | pt_BR |
dc.creator | Rivaney F. Oliveira | pt_BR |
dc.creator | Abisague Langbehn | pt_BR |
dc.date.accessioned | 2023-08-04T20:03:10Z | - |
dc.date.available | 2023-08-04T20:03:10Z | - |
dc.date.issued | 2021 | - |
dc.citation.issue | 2021 | pt_BR |
dc.citation.spage | 234 | pt_BR |
dc.citation.epage | 243 | pt_BR |
dc.identifier.doi | https://doi.org/10.26615/978-954-452-072-4_028 | pt_BR |
dc.identifier.isbn | 9789544520724 | pt_BR |
dc.identifier.uri | http://hdl.handle.net/1843/57494 | - |
dc.description.resumo | This study describes the development of a Portuguese Community-Question Answering benchmark in the domain of Diabetes Mellitus using a Recognizing Question Entailment (RQE) approach. Given a premise question, RQE aims to retrieve semantically similar, already answered, archived questions. We build a new Portuguese benchmark corpus with 785 pairs between premise questions and archived answered questions marked with relevance judgments by medical experts. Based on the benchmark corpus, we leveraged and evaluated several RQE approaches ranging from traditional information retrieval methods to novel large pre-trained language models and ensemble techniques using learn-to-rank approaches. Our experimental results show that a supervised transformer-based method trained with multiple languages and for multiple tasks (MUSE) outperforms the alternatives. Our results also show that ensembles of methods (stacking) as well as a traditional (light) information retrieval method (BM25) can produce competitive results. Finally, among the tested strategies, those that exploit only the question (not the answer), provide the best effectiveness-efficiency trade-off. Code is publicly available. | pt_BR |
dc.description.sponsorship | CNPq - Conselho Nacional de Desenvolvimento Científico e Tecnológico | pt_BR |
dc.description.sponsorship | FAPEMIG - Fundação de Amparo à Pesquisa do Estado de Minas Gerais | pt_BR |
dc.description.sponsorship | CAPES - Coordenação de Aperfeiçoamento de Pessoal de Nível Superior | pt_BR |
dc.format.mimetype | pt_BR | |
dc.language | eng | pt_BR |
dc.publisher | Universidade Federal de Minas Gerais | pt_BR |
dc.publisher.country | Brasil | pt_BR |
dc.publisher.department | FALE - FACULDADE DE LETRAS | pt_BR |
dc.publisher.department | ICX - DEPARTAMENTO DE CIÊNCIA DA COMPUTAÇÃO | pt_BR |
dc.publisher.department | MED - DEPARTAMENTO DE CLÍNICA MÉDICA | pt_BR |
dc.publisher.initials | UFMG | pt_BR |
dc.relation.ispartof | International Conference Recent Advances in Natural Language Processing | pt_BR |
dc.rights | Acesso Aberto | pt_BR |
dc.subject.other | Lingüística | pt_BR |
dc.subject.other | Ciência da Computação | pt_BR |
dc.subject.other | Diabetes | pt_BR |
dc.title | Evaluating recognizing question entailment methods for a Portuguese Community Question-Answering System about Diabetes Mellitus | pt_BR |
dc.type | Artigo de Evento | pt_BR |
dc.identifier.orcid | https://orcid.org/0000-0003-0200-3646 | pt_BR |
dc.identifier.orcid | https://orcid.org/0000-0002-8532-7701 | pt_BR |
dc.identifier.orcid | https://orcid.org/0000-0002-3150-3503 | pt_BR |
dc.identifier.orcid | https://orcid.org/0000-0002-0251-7172 | pt_BR |
dc.identifier.orcid | https://orcid.org/0000-0002-2075-3363 | pt_BR |
dc.identifier.orcid | https://orcid.org/0000-0001-5403-8360 | pt_BR |
dc.identifier.orcid | https://orcid.org/0000-0002-8548-7625 | pt_BR |
dc.identifier.orcid | https://orcid.org/0000-0003-4440-8123 | pt_BR |
Appears in Collections: | Artigo de Evento |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Evaluating Recognizing Question Entailment Methods for a Portuguese Community Question-Answering System about Diabetes Mellitus.pdf | 807.9 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.