Busca avançada
Ano de início
Entree


Low-resource AMR-to-Text Generation: A Study on Brazilian Portuguese

Texto completo
Autor(es):
Sobrevilla Cabezudo, Marco Antonio ; Salgueiro, Thiago Alexandre
Número total de Autores: 2
Tipo de documento: Artigo Científico
Fonte: PROCESAMIENTO DEL LENGUAJE NATURAL; v. N/A, n. 68, p. 13-pg., 2022-03-01.
Resumo

This work presents a study of how varied strategies for tackling low-resource AMR-to-text generation for three approaches are helpful in Brazilian Portuguese. Specifically, we explore the helpfulness of additional translated corpus, different granularity levels in input representation, and three preprocessing steps. Results show that translation is useful. However, it must be used in each approach differently. In addition, finer-grained representations as characters and subwords improve the performance and reduce the bias on the development set, and preprocessing steps are helpful in different contexts, being delexicalisation and preordering the most important ones. (AU)

Processo FAPESP: 19/07665-4 - Centro de Inteligência Artificial
Beneficiário:Fabio Gagliardi Cozman
Modalidade de apoio: Auxílio à Pesquisa - Programa eScience e Data Science - Centros de Pesquisa em Engenharia
Processo FAPESP: 13/07375-0 - CeMEAI - Centro de Ciências Matemáticas Aplicadas à Indústria
Beneficiário:Francisco Louzada Neto
Modalidade de apoio: Auxílio à Pesquisa - Centros de Pesquisa, Inovação e Difusão - CEPIDs