Logo do repositório
 
Publicação

Multilingual bi-encoder models for biomedical entity linking

2023-11Artigo científico Acesso aberto
Ver registo simples
dc.contributor.authorGuven, Zekeriya Anil
dc.contributor.authorLamúrias, André
dc.contributor.institutionDI - Departamento de Informática
dc.contributor.pblBlackwell Publishing Ltd
dc.date.accessioned2024-02-22T23:53:00Z
dc.date.available2024-02-22T23:53:00Z
dc.date.issued2023-11
dc.descriptionFunding Information: The authors would like to thank Prof. Dr. Murat Osman Unalir and Prof. Dr. Katja Hose. Publisher Copyright: © 2023 The Authors. Expert Systems published by John Wiley & Sons Ltd.
dc.description.abstractNatural language processing (NLP) is a field of study that focuses on data analysis on texts with certain methods. NLP includes tasks such as sentiment analysis, spam detection, entity linking, and question answering, to name a few. Entity linking is an NLP task that is used to map mentions specified in the text to the entities of a Knowledge Base. In this study, we analysed the efficacy of bi-encoder entity linking models for multilingual biomedical texts. Using surface-based, approximate nearest neighbour search and embedding approaches during the candidate generation phase, accuracy, and recall values were measured on language representation models such as BERT, SapBERT, BioBERT, and RoBERTa according to language and domain. The proposed entity linking framework was analysed on the BC5CDR and Cantemist datasets for English and Spanish, respectively. The framework achieved 76.75% accuracy for the BC5CDR and 60.19% for the Cantemist. In addition, the proposed framework was compared with previous studies. The results highlight the challenges that come with domain-specific multilingual datasets.en
dc.description.versionpublishersversion
dc.description.versionpublished
dc.format.extent14
dc.format.extent1670019
dc.identifier.doi10.1111/exsy.13388
dc.identifier.issn0266-4720
dc.identifier.otherPURE: 83890974
dc.identifier.otherPURE UUID: b4a99c40-01aa-4d44-aa0c-95663b856a68
dc.identifier.otherScopus: 85162707084
dc.identifier.otherWOS: 001009670900001
dc.identifier.urihttp://hdl.handle.net/10362/163981
dc.identifier.urlhttps://www.scopus.com/pages/publications/85162707084
dc.language.isoeng
dc.peerreviewedyes
dc.subjectbiomedical entity linking
dc.subjectdata analysis
dc.subjectentity linking
dc.subjectlanguage model
dc.subjectmultilingual analysis
dc.subjectnatural language processing
dc.subjectControl and Systems Engineering
dc.subjectTheoretical Computer Science
dc.subjectComputational Theory and Mathematics
dc.subjectArtificial Intelligence
dc.titleMultilingual bi-encoder models for biomedical entity linkingen
dc.typejournal article
degois.publication.issue9
degois.publication.titleExpert Systems
degois.publication.volume40
dspace.entity.typePublication
rcaap.rightsopenAccess

Ficheiros

Principais
A mostrar 1 - 1 de 1
Miniatura
Nome:
Multilingual_bi_encoder_models_for_biomedical_entity_linking.pdf
Tamanho:
1.59 MB
Formato:
Adobe Portable Document Format
Ver/Abrir

Coleções

Home collection (FCT)