Weighting-based semantic similarity measure based on topological parameters in semantic taxonomy

ABDULGABBAR SAIF, UMMI ZAKIAH ZAINODIN, Nazlia Omar, ABDULLAH SAEED GHAREB

Research output: Contribution to journalArticle

Abstract

Semantic measures are used in handling different issues in several research areas, such as artificial intelligence, natural language processing, knowledge engineering, bioinformatics, and information retrieval. Hierarchical feature-based semantic measures have been proposed to estimate the semantic similarity between two concepts/words depending on the features extracted from a semantic taxonomy (hierarchy) of a given lexical source. The central issue in these measures is the constant weighting assumption that all elements in the semantic representation of the concept possess the same relevance. In this paper, a new weighting-based semantic similarity measure is proposed to address the issues in hierarchical feature-based measures. Four mechanisms are introduced to weigh the degree of relevance of features in the semantic representation of a concept by using topological parameters (edge, depth, descendants, and density) in a semantic taxonomy. With the semantic taxonomy of WordNet, the proposed semantic measure is evaluated for word semantic similarity in four gold-standard datasets. Experimental results show that the proposed measure outperforms hierarchical feature-based semantic measures in all the datasets. Comparison results also imply that the proposed measure is more effective than information-content measures in measuring semantic similarity.

Original languageEnglish
Pages (from-to)1-26
Number of pages26
JournalNatural Language Engineering
DOIs
Publication statusAccepted/In press - 4 Jun 2018

Fingerprint

Taxonomies
weighting
taxonomy
Semantics
semantics
Taxonomy
Semantic Similarity
Knowledge engineering
information content
gold standard
artificial intelligence
Bioinformatics
Information retrieval
information retrieval
Artificial intelligence
Gold
engineering

ASJC Scopus subject areas

  • Software
  • Language and Linguistics
  • Linguistics and Language
  • Artificial Intelligence

Cite this

Weighting-based semantic similarity measure based on topological parameters in semantic taxonomy. / SAIF, ABDULGABBAR; ZAINODIN, UMMI ZAKIAH; Omar, Nazlia; GHAREB, ABDULLAH SAEED.

In: Natural Language Engineering, 04.06.2018, p. 1-26.

Research output: Contribution to journalArticle

SAIF, ABDULGABBAR ; ZAINODIN, UMMI ZAKIAH ; Omar, Nazlia ; GHAREB, ABDULLAH SAEED. / Weighting-based semantic similarity measure based on topological parameters in semantic taxonomy. In: Natural Language Engineering. 2018 ; pp. 1-26.
@article{9af49d6114ed466b8f952391f70e2950,
title = "Weighting-based semantic similarity measure based on topological parameters in semantic taxonomy",
abstract = "Semantic measures are used in handling different issues in several research areas, such as artificial intelligence, natural language processing, knowledge engineering, bioinformatics, and information retrieval. Hierarchical feature-based semantic measures have been proposed to estimate the semantic similarity between two concepts/words depending on the features extracted from a semantic taxonomy (hierarchy) of a given lexical source. The central issue in these measures is the constant weighting assumption that all elements in the semantic representation of the concept possess the same relevance. In this paper, a new weighting-based semantic similarity measure is proposed to address the issues in hierarchical feature-based measures. Four mechanisms are introduced to weigh the degree of relevance of features in the semantic representation of a concept by using topological parameters (edge, depth, descendants, and density) in a semantic taxonomy. With the semantic taxonomy of WordNet, the proposed semantic measure is evaluated for word semantic similarity in four gold-standard datasets. Experimental results show that the proposed measure outperforms hierarchical feature-based semantic measures in all the datasets. Comparison results also imply that the proposed measure is more effective than information-content measures in measuring semantic similarity.",
author = "ABDULGABBAR SAIF and ZAINODIN, {UMMI ZAKIAH} and Nazlia Omar and GHAREB, {ABDULLAH SAEED}",
year = "2018",
month = "6",
day = "4",
doi = "10.1017/S1351324918000190",
language = "English",
pages = "1--26",
journal = "Natural Language Engineering",
issn = "1351-3249",
publisher = "Cambridge University Press",

}

TY - JOUR

T1 - Weighting-based semantic similarity measure based on topological parameters in semantic taxonomy

AU - SAIF, ABDULGABBAR

AU - ZAINODIN, UMMI ZAKIAH

AU - Omar, Nazlia

AU - GHAREB, ABDULLAH SAEED

PY - 2018/6/4

Y1 - 2018/6/4

N2 - Semantic measures are used in handling different issues in several research areas, such as artificial intelligence, natural language processing, knowledge engineering, bioinformatics, and information retrieval. Hierarchical feature-based semantic measures have been proposed to estimate the semantic similarity between two concepts/words depending on the features extracted from a semantic taxonomy (hierarchy) of a given lexical source. The central issue in these measures is the constant weighting assumption that all elements in the semantic representation of the concept possess the same relevance. In this paper, a new weighting-based semantic similarity measure is proposed to address the issues in hierarchical feature-based measures. Four mechanisms are introduced to weigh the degree of relevance of features in the semantic representation of a concept by using topological parameters (edge, depth, descendants, and density) in a semantic taxonomy. With the semantic taxonomy of WordNet, the proposed semantic measure is evaluated for word semantic similarity in four gold-standard datasets. Experimental results show that the proposed measure outperforms hierarchical feature-based semantic measures in all the datasets. Comparison results also imply that the proposed measure is more effective than information-content measures in measuring semantic similarity.

AB - Semantic measures are used in handling different issues in several research areas, such as artificial intelligence, natural language processing, knowledge engineering, bioinformatics, and information retrieval. Hierarchical feature-based semantic measures have been proposed to estimate the semantic similarity between two concepts/words depending on the features extracted from a semantic taxonomy (hierarchy) of a given lexical source. The central issue in these measures is the constant weighting assumption that all elements in the semantic representation of the concept possess the same relevance. In this paper, a new weighting-based semantic similarity measure is proposed to address the issues in hierarchical feature-based measures. Four mechanisms are introduced to weigh the degree of relevance of features in the semantic representation of a concept by using topological parameters (edge, depth, descendants, and density) in a semantic taxonomy. With the semantic taxonomy of WordNet, the proposed semantic measure is evaluated for word semantic similarity in four gold-standard datasets. Experimental results show that the proposed measure outperforms hierarchical feature-based semantic measures in all the datasets. Comparison results also imply that the proposed measure is more effective than information-content measures in measuring semantic similarity.

UR - http://www.scopus.com/inward/record.url?scp=85047873526&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85047873526&partnerID=8YFLogxK

U2 - 10.1017/S1351324918000190

DO - 10.1017/S1351324918000190

M3 - Article

SP - 1

EP - 26

JO - Natural Language Engineering

JF - Natural Language Engineering

SN - 1351-3249

ER -