Unveiling the relationship between complex networks metrics and word senses


Autoria(s): Amancio, Diego R.; Oliveira Junior, Osvaldo Novais de; Costa, Luciano da Fontoura
Contribuinte(s)

UNIVERSIDADE DE SÃO PAULO

Data(s)

05/11/2013

05/11/2013

2012

Resumo

The automatic disambiguation of word senses (i.e., the identification of which of the meanings is used in a given context for a word that has multiple meanings) is essential for such applications as machine translation and information retrieval, and represents a key step for developing the so-called Semantic Web. Humans disambiguate words in a straightforward fashion, but this does not apply to computers. In this paper we address the problem of Word Sense Disambiguation (WSD) by treating texts as complex networks, and show that word senses can be distinguished upon characterizing the local structure around ambiguous words. Our goal was not to obtain the best possible disambiguation system, but we nevertheless found that in half of the cases our approach outperforms traditional shallow methods. We show that the hierarchical connectivity and clustering of words are usually the most relevant features for WSD. The results reported here shed light on the relationship between semantic and structural parameters of complex networks. They also indicate that when combined with traditional techniques the complex network approach may be useful to enhance the discrimination of senses in large texts. Copyright (C) EPLA, 2012

CNPq (Brazil)

CNPq (Brazil)

FAPESP [2010/00927-9]

FAPESP

Identificador

EPL, MULHOUSE, v. 98, n. 1, supl. 1, Part 2, pp. 3063-3070, APR, 2012

0295-5075

http://www.producao.usp.br/handle/BDPI/40928

10.1209/0295-5075/98/18002

http://dx.doi.org/10.1209/0295-5075/98/18002

Idioma(s)

eng

Publicador

EPL ASSOCIATION, EUROPEAN PHYSICAL SOCIETY

MULHOUSE

Relação

EPL

Direitos

restrictedAccess

Copyright EPL ASSOCIATION, EUROPEAN PHYSICAL SOCIETY

Palavras-Chave #PHYSICS, MULTIDISCIPLINARY
Tipo

article

original article

publishedVersion