Characterization of temporal complementarity: fundamentals for multi-document summarization

Complementarity is a usual multi-document phenomenon that commonly occurs among news texts about the same event. From a set of sentence pairs (in Portuguese) manually annotated with CST (Cross-Document Structure Theory) relations (Historical background and Follow-up) that make explicit the temporal...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: CAPES e FAPESP, Souza, Jackson Wilke da Cruz, Felippo, Ariani Di
Formato: Artículo publishedVersion
Lenguaje:Portugués
Inglés
Publicado: ALFA: Revista de Linguística 2018
Materias:
Linguistic description; Complementarity; CST; Multi-document Summarization; Natural Language Processing;
Descrição linguística; Complementaridade; CST; Sumarização Multidocumento; Processamento Automático de Língua Natural;
Acceso en línea:https://periodicos.fclar.unesp.br/alfa/article/view/9204
http://biblioteca.clacso.edu.ar/gsdl/cgi-bin/library.cgi?a=d&c=br/br-048&d=article9204oai
Aporte de:
Red de Bibliotecas Virtuales de Ciencias Sociales (CLACSO) de Consejo Latinoamericano de Ciencias Sociales
id I16-R122-article9204oai
record_format dspace
institution Consejo Latinoamericano de Ciencias Sociales
institution_str I-16
repository_str R-122
collection Red de Bibliotecas Virtuales de Ciencias Sociales (CLACSO)
language Portugués
Inglés
topic Linguistic description; Complementarity; CST; Multi-document Summarization; Natural Language Processing;
Descrição linguística; Complementaridade; CST; Sumarização Multidocumento; Processamento Automático de Língua Natural;
spellingShingle Linguistic description; Complementarity; CST; Multi-document Summarization; Natural Language Processing;
Descrição linguística; Complementaridade; CST; Sumarização Multidocumento; Processamento Automático de Língua Natural;
CAPES e FAPESP
Souza, Jackson Wilke da Cruz
Felippo, Ariani Di
Characterization of temporal complementarity: fundamentals for multi-document summarization
topic_facet Linguistic description; Complementarity; CST; Multi-document Summarization; Natural Language Processing;
Descrição linguística; Complementaridade; CST; Sumarização Multidocumento; Processamento Automático de Língua Natural;
description Complementarity is a usual multi-document phenomenon that commonly occurs among news texts about the same event. From a set of sentence pairs (in Portuguese) manually annotated with CST (Cross-Document Structure Theory) relations (Historical background and Follow-up) that make explicit the temporal complementary among the sentences, we identified a potential set of linguistic attributes of such complementary. Using Machine Learning algorithms, we evaluate the capacity of the attributes to discriminate between Historical background and Follow-up. JRip learned a small set of rules with high accuracy. Based on a set of 5 rules, the classifier discriminates the CST relations with 80% of accuracy. According to the rules, the occurrence of temporal expression in sentence 2 is the most discriminative feature in the task. As a contribution, the JRip classifier can improve the performance of the CST-discourse parsers for Portuguese.
format Artículo
publishedVersion
Artículo
publishedVersion
author CAPES e FAPESP
Souza, Jackson Wilke da Cruz
Felippo, Ariani Di
author_facet CAPES e FAPESP
Souza, Jackson Wilke da Cruz
Felippo, Ariani Di
author_sort CAPES e FAPESP
title Characterization of temporal complementarity: fundamentals for multi-document summarization
title_short Characterization of temporal complementarity: fundamentals for multi-document summarization
title_full Characterization of temporal complementarity: fundamentals for multi-document summarization
title_fullStr Characterization of temporal complementarity: fundamentals for multi-document summarization
title_full_unstemmed Characterization of temporal complementarity: fundamentals for multi-document summarization
title_sort characterization of temporal complementarity: fundamentals for multi-document summarization
publisher ALFA: Revista de Linguística
publishDate 2018
url https://periodicos.fclar.unesp.br/alfa/article/view/9204
http://biblioteca.clacso.edu.ar/gsdl/cgi-bin/library.cgi?a=d&c=br/br-048&d=article9204oai
work_keys_str_mv AT capesefapesp characterizationoftemporalcomplementarityfundamentalsformultidocumentsummarization
AT souzajacksonwilkedacruz characterizationoftemporalcomplementarityfundamentalsformultidocumentsummarization
AT felippoarianidi characterizationoftemporalcomplementarityfundamentalsformultidocumentsummarization
AT capesefapesp caracterizacaodacomplementaridadetemporalsubsidiosparasumarizacaoautomaticamultidocumento
AT souzajacksonwilkedacruz caracterizacaodacomplementaridadetemporalsubsidiosparasumarizacaoautomaticamultidocumento
AT felippoarianidi caracterizacaodacomplementaridadetemporalsubsidiosparasumarizacaoautomaticamultidocumento
bdutipo_str Repositorios
_version_ 1764820439862870017

Ejemplares similares