TY  - JOUR
Y1  - 2021///
A1  - Hamad, A.H.
A1  - Mahmood, A.A.
A1  - Abed, S.A.
A1  - Ying, X.
UR  - https://www.scopus.com/inward/record.uri?eid=2-s2.0-85122016027&doi=10.3233%2fJIFS-210934&partnerID=40&md5=d12db3484c46e6d859fc6930d658d274
N1  - cited By 1
JF  - Journal of Intelligent and Fuzzy Systems
VL  - 41
IS  - 6
TI  - Semantic relatedness maximisation for word sense disambiguation using a hybrid firefly algorithm
KW  - Bioluminescence; Learning algorithms; Local search (optimization); Semantic Web; Semantics; Swarm intelligence
KW  -  Firefly algorithms; High-accuracy; Local search; Machine translations; Metaheuristic; Performance; Related works; Semantic relatedness; Text Summarisation; Word Sense Disambiguation
KW  -  Natural language processing systems
N2  - Word sense disambiguation (WSD) refers to determining the right meaning of a vague word using its context. The WSD intermediately consolidates the performance of final tasks to achieve high accuracy. Mainly, a WSD solution improves the accuracy of text summarisation, information retrieval, and machine translation. This study addresses the WSD by assigning a set of senses to a given text, where the maximum semantic relatedness is obtained. This is achieved by proposing a swarm intelligence method, called firefly algorithm (FA) to find the best possible set of senses. Because of the FA is based on a population of solutions, it explores the problem space more than exploiting it. Hence, we hybridise the FA with a one-point search algorithm to improve its exploitation capacity. Practically, this hybridisation aims to maximise the semantic relatedness of an eligible set of senses. In this study, the semantic relatedness is measured by proposing a glosses-overlapping method enriched by the notion of information content. To evaluate the proposed method, we have conducted intensive experiments with comparisons to the related works based on benchmark datasets. The obtained results showed that our method is comparable if not superior to the related works. Thus, the proposed method can be considered as an efficient solver for the WSD task. © 2021 - IOS Press. All rights reserved.
SN  - 10641246
EP  - 7061
ID  - scholars15596
AV  - none
SP  - 7047
PB  - IOS Press BV
ER  -