Guardado en:
Detalles Bibliográficos
Autores principales: Pernes, Diogo, Correia, Gonçalo M., Mendes, Afonso
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2410.00502
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910626991833088
author Pernes, Diogo
Correia, Gonçalo M.
Mendes, Afonso
author_facet Pernes, Diogo
Correia, Gonçalo M.
Mendes, Afonso
contents Cross-lingual summarization aims to bridge language barriers by summarizing documents in different languages. However, ensuring semantic coherence across languages is an overlooked challenge and can be critical in several contexts. To fill this gap, we introduce multi-target cross-lingual summarization as the task of summarizing a document into multiple target languages while ensuring that the produced summaries are semantically similar. We propose a principled re-ranking approach to this problem and a multi-criteria evaluation protocol to assess semantic coherence across target languages, marking a first step that will hopefully stimulate further research on this problem.
format Preprint
id arxiv_https___arxiv_org_abs_2410_00502
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Multi-Target Cross-Lingual Summarization: a novel task and a language-neutral approach
Pernes, Diogo
Correia, Gonçalo M.
Mendes, Afonso
Computation and Language
Artificial Intelligence
Machine Learning
Cross-lingual summarization aims to bridge language barriers by summarizing documents in different languages. However, ensuring semantic coherence across languages is an overlooked challenge and can be critical in several contexts. To fill this gap, we introduce multi-target cross-lingual summarization as the task of summarizing a document into multiple target languages while ensuring that the produced summaries are semantically similar. We propose a principled re-ranking approach to this problem and a multi-criteria evaluation protocol to assess semantic coherence across target languages, marking a first step that will hopefully stimulate further research on this problem.
title Multi-Target Cross-Lingual Summarization: a novel task and a language-neutral approach
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2410.00502