PUCRJ-PUCPR-UFMG at eHealth-KD Challenge 2021: a multilingual BERT-based system for joint entity recognition and relation extraction

Página do item simplificado
dc.creatorThiago Castro Ferreira
dc.creatorJoão Vitor Andrioli de Souza
dc.creatorLucas Ferro Antunes de Oliveira
dc.creatorLucas Emanuel Silva e Oliveira
dc.creatorClaudia Moro Barra
dc.creatorEmerson Cabrera Paraíso
dc.creatorYohan Bonescki Gumiel
dc.creatorAdriana Silvina Pagano
dc.creatorGiovanni Pazini Meneghel Paiva
dc.creatorElisa Terumi Rubel Schneider
dc.creatorLucas Pavanelli
dc.date.accessioned2024-03-21T18:20:27Z
dc.date.accessioned2025-09-09T00:27:29Z
dc.date.available2024-03-21T18:20:27Z
dc.date.issued2021
dc.format.mimetypepdf
dc.identifier.issn1613-0073
dc.identifier.urihttps://hdl.handle.net/1843/66341
dc.languageeng
dc.publisherUniversidade Federal de Minas Gerais
dc.relation.ispartofIberian Languages Evaluation Forum
dc.rightsAcesso Aberto
dc.subjectProcessamento da linguagem natural (Computação)
dc.subjectInformática na medicina
dc.subject.othereHealth
dc.subject.otherEntity recognition
dc.subject.otherRelation extraction
dc.subject.otherBERT
dc.subject.otherDeep learning
dc.titlePUCRJ-PUCPR-UFMG at eHealth-KD Challenge 2021: a multilingual BERT-based system for joint entity recognition and relation extraction
dc.typeArtigo de evento
local.citation.epage691
local.citation.spage683
local.description.resumoThis study introduces the system submitted to the eHealthKD Challenge 2021 by the PUCRJ-PUCPR-UFMG team. We proposed a multilingual BERT-based system for joint entity recognition and relation extraction in multidomain texts. Our end-to-end multitasking model benefits from the transformer architecture, which has proved to capture better the global dependencies of the input text. Also, the use of a multilingual model contributed to our system to perform well even in the set of tests containing non-Spanish sentences. Our system ranked first in the entity recognition task and second in the Main scenario, where both tasks of entity recognition and relation extraction had to be solved. The full code of our approach and more details of the implementation are publicly available
local.identifier.orcidhttps://orcid.org/0000-0003-0200-3646
local.identifier.orcidhttps://orcid.org/0000-0002-8950-0890
local.identifier.orcidhttps://orcid.org/0000-0003-4052-7993
local.identifier.orcidhttps://orcid.org/0000-0002-8921-5598
local.identifier.orcidhttps://orcid.org/0000-0003-2228-7965
local.identifier.orcidhttps://orcid.org/0000-0002-3150-3503
local.identifier.orcidhttps://orcid.org/0000-0002-6740-7855
local.identifier.orcidhttps://orcid.org/0000-0003-2637-3086
local.identifier.orcidhttps://orcid.org/0000-0003-1811-5087
local.identifier.orcidhttps://orcid.org/0000-0002-9789-9547
local.identifier.orcidhttps://orcid.org/0000-0001-8239-2930
local.publisher.countryBrasil
local.publisher.departmentFALE - FACULDADE DE LETRAS
local.publisher.initialsUFMG
local.url.externahttps://ceur-ws.org/Vol-2943/ehealth_paper3.pdf

Arquivos

Pacote original

Agora exibindo 1 - 1 de 1
Imagem de Miniatura
Nome:
PUCRJ-PUCPR-UFMG at eHealth-KD Challenge 2021 a multilingual BERT-based system for joint entity recognition and relation extraction.pdf
Tamanho:
605.23 KB
Formato:
Adobe Portable Document Format
Baixar

Licença do pacote

Agora exibindo 1 - 1 de 1
Imagem de Miniatura
Nome:
License.txt
Tamanho:
1.99 KB
Formato:
Plain Text
Descrição:
Baixar

Coleções

Artigo de Evento

Logo UFMG