Word vs. Class-Based Word Sense Disambiguation

Please use this identifier to cite or link to this item: http://hdl.handle.net/10045/50835
Información del item - Informació de l'item - Item information
Title: Word vs. Class-Based Word Sense Disambiguation
Authors: Izquierdo Beviá, Rubén | Suárez Cueto, Armando | Rigau Claramunt, German
Research Group/s: Procesamiento del Lenguaje y Sistemas de Información (GPLSI)
Center, Department or Service: Universidad de Alicante. Departamento de Lenguajes y Sistemas Informáticos
Keywords: Word Sense Disambiguation | WordNet
Knowledge Area: Lenguajes y Sistemas Informáticos
Issue Date: Sep-2015
Publisher: AI Access Foundation
Citation: Journal of Artificial Intelligence Research. 2015, 54: 83-122. doi:10.1613/jair.4727
Abstract: As empirically demonstrated by the Word Sense Disambiguation (WSD) tasks of the last SensEval/SemEval exercises, assigning the appropriate meaning to words in context has resisted all attempts to be successfully addressed. Many authors argue that one possible reason could be the use of inappropriate sets of word meanings. In particular, WordNet has been used as a de-facto standard repository of word meanings in most of these tasks. Thus, instead of using the word senses defined in WordNet, some approaches have derived semantic classes representing groups of word senses. However, the meanings represented by WordNet have been only used for WSD at a very fine-grained sense level or at a very coarse-grained semantic class level (also called SuperSenses). We suspect that an appropriate level of abstraction could be on between both levels. The contributions of this paper are manifold. First, we propose a simple method to automatically derive semantic classes at intermediate levels of abstraction covering all nominal and verbal WordNet meanings. Second, we empirically demonstrate that our automatically derived semantic classes outperform classical approaches based on word senses and more coarse-grained sense groupings. Third, we also demonstrate that our supervised WSD system benefits from using these new semantic classes as additional semantic features while reducing the amount of training examples. Finally, we also demonstrate the robustness of our supervised semantic class-based WSD system when tested on out of domain corpus.
Sponsor: This work has been partially supported by the NewsReader project (ICT-2011-316404), the Spanish project SKaTer (TIN2012-38584-C06-02).
URI: http://hdl.handle.net/10045/50835
ISSN: 1076-9757 (Print) | 1943-5037 (Online)
DOI: 10.1613/jair.4727
Language: eng
Type: info:eu-repo/semantics/article
Rights: © 2015 AI Access Foundation
Peer Review: si
Publisher version: http://dx.doi.org/10.1613/jair.4727
Appears in Collections:INV - GPLSI - Artículos de Revistas

Files in This Item:
Files in This Item:
File Description SizeFormat 
Thumbnail2015_Izquierdo_etal_JAIR.pdf392,37 kBAdobe PDFOpen Preview

Items in RUA are protected by copyright, with all rights reserved, unless otherwise indicated.