Utilize este identificador para referenciar este registo:
http://hdl.handle.net/10071/11022
Autoria: | Marujo, L. Ling, W. Ribeiro, R. Gershman, A. Carbonell, J. de Matos, D. Neto, J. P. |
Data: | 2016 |
Título próprio: | Exploring events and distributed representations of text in multi-document summarization |
Volume: | 94 |
Paginação: | 33 - 42 |
ISSN: | 0950-7051 |
DOI (Digital Object Identifier): | 10.1016/j.knosys.2015.11.005 |
Palavras-chave: | Multi-document summarization Extractive summarization Event detection Distributed representations of text |
Resumo: | In this article, we explore an event detection framework to improve multi-document summarization. Our approach is based on a two-stage single-document method that extracts a collection of key phrases, which are then used in a centrality-as-relevance passage retrieval model. We explore how to adapt this single-document method for multi-document summarization methods that are able to use event information. The event detection method is based on Fuzzy Fingerprint, which is a supervised method trained on documents with annotated event tags. To cope with the possible usage of different terms to describe the same event, we explore distributed representations of text in the form of word embeddings, which contributed to improve the summarization results. The proposed summarization methods are based on the hierarchical combination of single-document summaries. The automatic evaluation and human study performed show that these methods improve upon current state-of-the-art multi-document summarization systems on two mainstream evaluation datasets, DUC 2007 and TAC 2009. We show a relative improvement in ROUGE-1 scores of 16% for TAC 2009 and of 17% for DUC 2007. |
Arbitragem científica: | yes |
Acesso: | Acesso Aberto |
Aparece nas coleções: | CTI-RI - Artigos em revistas científicas internacionais com arbitragem científica |
Ficheiros deste registo:
Ficheiro | Descrição | Tamanho | Formato | |
---|---|---|---|---|
article.pdf | Pré-print | 462,08 kB | Adobe PDF | Ver/Abrir |
Todos os registos no repositório estão protegidos por leis de copyright, com todos os direitos reservados.