Spreading semantic information by Word Sense Disambiguation

•A Word Sense Disambiguation (WSD) knowledge-based system is presented.•A multidimensional network obtained from different lexical resources is described.•A detailed description of graph creation and algorithms used is provided.•A detailed comparative among relevant WSD approaches is presented.•An e...

Full description

Saved in:
Bibliographic Details
Published in:Knowledge-based systems 2017-09, Vol.132, p.47-61
Main Authors: Gutiérrez, Yoan, Vázquez, Sonia, Montoyo, Andrés
Format: Article
Language:English
Subjects:
Algorithms
Corpus analysis
Expert systems
Graph-based
Information dissemination
Knowledge-based
Machine translation
Natural language
Natural language processing
Pagerank
Personal communication
Recommender systems
Search engines
Semantics
Verbal tasks
Word Sense Disambiguation
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•A Word Sense Disambiguation (WSD) knowledge-based system is presented.•A multidimensional network obtained from different lexical resources is described.•A detailed description of graph creation and algorithms used is provided.•A detailed comparative among relevant WSD approaches is presented.•An extensive evaluation and analysis of the obtained results is provided.•A description about the benefits of this WSD proposal in other Natural Language Processing tasks is provided. This paper presents an unsupervised approach to solve semantic ambiguity based on the integration of the Personalized PageRank algorithm with word-sense frequency information. Natural Language tasks such as Machine Translation or Recommender Systems are likely to be enriched by our approach, which includes semantic information that obtains the appropriate word-sense via support from two sources: a multidimensional network that includes a set of different resources (i.e. WordNet, WordNet Domains, WordNet Affect, SUMO and Semantic Classes); and the information provided by word-sense frequencies and word-sense collocation from the SemCor Corpus. Our series of results were analyzed and compared against the results of several renowned studies using SensEval-2, SensEval-3 and SemEval-2013 datasets. After conducting several experiments, our procedure produced the best results in the unsupervised procedure category taking SensEval campaigns rankings as reference.
ISSN:0950-7051
1872-7409
DOI:10.1016/j.knosys.2017.06.013