Please use this identifier to cite or link to this item:
http://hdl.handle.net/1843/66342
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.creator | Rossana Cunha | pt_BR |
dc.creator | Thiago Castro Ferreira | pt_BR |
dc.creator | Adriana Silvina Pagano | pt_BR |
dc.creator | Fábio Alves da Silva Júnior | pt_BR |
dc.date.accessioned | 2024-03-21T18:48:49Z | - |
dc.date.available | 2024-03-21T18:48:49Z | - |
dc.date.issued | 2020-12-11 | - |
dc.citation.issue | 28 | pt_BR |
dc.citation.spage | 2261 | pt_BR |
dc.citation.epage | 2272 | pt_BR |
dc.identifier.doi | https://doi.org/10.18653/v1/2020.coling-main.205 | pt_BR |
dc.identifier.isbn | 9781952148279 | pt_BR |
dc.identifier.uri | http://hdl.handle.net/1843/66342 | - |
dc.description.resumo | Data-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.sponsorship | FAPEMIG - Fundação de Amparo à Pesquisa do Estado de Minas Gerais | 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.initials | UFMG | pt_BR |
dc.relation.ispartof | International Conference on Computational Linguistics | pt_BR |
dc.rights | Acesso Aberto | pt_BR |
dc.subject.other | Processamento da linguagem natural (Computação) | pt_BR |
dc.subject.other | Linguística - Processamento de dados | pt_BR |
dc.title | Referring to what you know and do not know: making referring expression generation models generalize to unseen entities | 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/0000-0002-3150-3503 | pt_BR |
dc.identifier.orcid | https://orcid.org/0000-0003-1089-4864 | pt_BR |
Appears in Collections: | Artigo de Evento |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Referring to what you know and do not know making referring expression generation models generalize to unseen entities.pdf | 310.95 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.