1. Repositório Institucional da UFMG
  2. Publicações Científicas e Culturais
  3. Artigo de Evento
Please use this identifier to cite or link to this item: http://hdl.handle.net/1843/66342
Full metadata record
DC FieldValueLanguage
dc.creatorRossana Cunhapt_BR
dc.creatorThiago Castro Ferreirapt_BR
dc.creatorAdriana Silvina Paganopt_BR
dc.creatorFábio Alves da Silva Júniorpt_BR
dc.date.accessioned2024-03-21T18:48:49Z-
dc.date.available2024-03-21T18:48:49Z-
dc.date.issued2020-12-11-
dc.citation.issue28pt_BR
dc.citation.spage2261pt_BR
dc.citation.epage2272pt_BR
dc.identifier.doihttps://doi.org/10.18653/v1/2020.coling-main.205pt_BR
dc.identifier.isbn9781952148279pt_BR
dc.identifier.urihttp://hdl.handle.net/1843/66342-
dc.description.resumoData-to-text Natural Language Generation (NLG) is the computational process of generating natural language in the form of text or voice from non-linguistic data. A core micro-planning task within NLG is referring expression generation (REG), which aims to automatically generate noun phrases to refer to entities mentioned as discourse unfolds. A limitation of novel REG models is not being able to generate referring expressions to entities not encountered during the training process. To solve this problem, we propose two extensions to NeuralREG, a state-ofthe-art encoder-decoder REG model. The first is a copy mechanism, whereas the second consists of representing the gender and type of the referent as inputs to the model. Drawing on the results of automatic and human evaluation as well as an ablation study using the WebNLG corpus, we contend that our proposal contributes to the generation of more meaningful referring expressions to unseen entities than the original system and related work. Code and all produced data are publicly available.pt_BR
dc.description.sponsorshipFAPEMIG - Fundação de Amparo à Pesquisa do Estado de Minas Geraispt_BR
dc.format.mimetypepdfpt_BR
dc.languageengpt_BR
dc.publisherUniversidade Federal de Minas Geraispt_BR
dc.publisher.countryBrasilpt_BR
dc.publisher.departmentFALE - FACULDADE DE LETRASpt_BR
dc.publisher.initialsUFMGpt_BR
dc.relation.ispartofInternational Conference on Computational Linguisticspt_BR
dc.rightsAcesso Abertopt_BR
dc.subject.otherProcessamento da linguagem natural (Computação)pt_BR
dc.subject.otherLinguística - Processamento de dadospt_BR
dc.titleReferring to what you know and do not know: making referring expression generation models generalize to unseen entitiespt_BR
dc.typeArtigo de Eventopt_BR
dc.identifier.orcidhttps://orcid.org/0000-0003-0200-3646pt_BR
dc.identifier.orcidhttps://orcid.org/0000-0002-3150-3503pt_BR
dc.identifier.orcidhttps://orcid.org/0000-0003-1089-4864pt_BR
Appears in Collections:Artigo de Evento

Files in This Item:
File Description SizeFormat 
Referring to what you know and do not know making referring expression generation models generalize to unseen entities.pdf310.95 kBAdobe PDFView/Open
Show simple item record


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.