Referring to what you know and do not know: making referring expression generation models generalize to unseen entities

Página do item simplificado
dc.creatorRossana Cunha
dc.creatorThiago Castro Ferreira
dc.creatorAdriana Silvina Pagano
dc.creatorFábio Alves da Silva Júnior
dc.date.accessioned2024-03-21T18:48:49Z
dc.date.accessioned2025-09-08T22:53:14Z
dc.date.available2024-03-21T18:48:49Z
dc.date.issued2020-12-11
dc.description.sponsorshipFAPEMIG - Fundação de Amparo à Pesquisa do Estado de Minas Gerais
dc.format.mimetypepdf
dc.identifier.doihttps://doi.org/10.18653/v1/2020.coling-main.205
dc.identifier.isbn9781952148279
dc.identifier.urihttps://hdl.handle.net/1843/66342
dc.languageeng
dc.publisherUniversidade Federal de Minas Gerais
dc.relation.ispartofInternational Conference on Computational Linguistics
dc.rightsAcesso Aberto
dc.subjectProcessamento da linguagem natural (Computação)
dc.subjectLinguística - Processamento de dados
dc.titleReferring to what you know and do not know: making referring expression generation models generalize to unseen entities
dc.typeArtigo de evento
local.citation.epage2272
local.citation.issue28
local.citation.spage2261
local.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.
local.identifier.orcidhttps://orcid.org/0000-0003-0200-3646
local.identifier.orcidhttps://orcid.org/0000-0002-3150-3503
local.identifier.orcidhttps://orcid.org/0000-0003-1089-4864
local.publisher.countryBrasil
local.publisher.departmentFALE - FACULDADE DE LETRAS
local.publisher.initialsUFMG

Arquivos

Pacote original

Agora exibindo 1 - 1 de 1
Imagem de Miniatura
Nome:
Referring to what you know and do not know making referring expression generation models generalize to unseen entities.pdf
Tamanho:
310.95 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