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

Rossana Cunha; Thiago Castro Ferreira; Adriana Silvina Pagano; Fábio Alves da Silva Júnior

Use este identificador para citar ou linkar para este item: http://hdl.handle.net/1843/66342

Tipo:	Artigo de Evento
Título:	Referring to what you know and do not know: making referring expression generation models generalize to unseen entities
Autor(es):	Rossana Cunha Thiago Castro Ferreira Adriana Silvina Pagano Fábio Alves da Silva Júnior
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.
Assunto:	Processamento da linguagem natural (Computação) Linguística - Processamento de dados
Idioma:	eng
País:	Brasil
Editor:	Universidade Federal de Minas Gerais
Sigla da Instituição:	UFMG
Departamento:	FALE - FACULDADE DE LETRAS
Tipo de Acesso:	Acesso Aberto
Identificador DOI:	https://doi.org/10.18653/v1/2020.coling-main.205
URI:	http://hdl.handle.net/1843/66342
Data do documento:	11-Dez-2020
metadata.dc.relation.ispartof:	International Conference on Computational Linguistics
Aparece nas coleções:	Artigo de Evento

Arquivos associados a este item:

Arquivo	Descrição	Tamanho	Formato
Referring to what you know and do not know making referring expression generation models generalize to unseen entities.pdf		310.95 kB	Adobe PDF	Visualizar/Abrir

Mostrar registro completo do item Visualizar estatísticas