Combination Features for Semantic Similarity Measure

Dat HUYNH, Dat TRAN, Wanli MA

Research output: A Conference proceeding or a Chapter in BookConference contribution

2 Citations (Scopus)

Abstract

Computing the semantic similarity between words is one of the key tasks in many language-based applications. Recent work has focused on using contextual clues for semantic similarity computation. In this paper, we propose a method to the measure semantic similarity between words using plain text contents. It takes into account information attributes (local) and topic information (global) of words to disclose their semantic similarity scores. The method models the representation of a word as a high dimensional vector of word attributes and latent topics. Thus, the semantic similarity between two words is measured by the semantic distance between their respective vectors. We have tested the proposed method on WordSimilarity-353 dataset. The empirical results have shown the combination features contribute to improve the semantic similarity results the dataset in comparison with previous work on the same task using plain text contents.

Original languageEnglish
Title of host publicationProceedings of the International MultiConference of Engineers and Computer Scientists 2014
EditorsS.I Ao, Oscar Castillo, Craig Douglas, David Dagan Feng, Jeong-A Lee
Place of PublicationHong Kong
PublisherNewswood Limited
Pages324-327
Number of pages4
Volume2209
ISBN (Print)9783319116983
Publication statusPublished - 2014
EventInternational MultiConference of Engineers and Computer Scientists 2014 - Hong Kong, Hong Kong, China
Duration: 12 Mar 201414 Mar 2014

Publication series

NameLecture Notes in Engineering and Computer Science
ISSN (Print)2078-0958

Conference

ConferenceInternational MultiConference of Engineers and Computer Scientists 2014
Abbreviated titleIMECS 2014
CountryChina
CityHong Kong
Period12/03/1414/03/14

Fingerprint

Semantics

Cite this

HUYNH, D., TRAN, D., & MA, W. (2014). Combination Features for Semantic Similarity Measure. In S. I. Ao, O. Castillo, C. Douglas, D. D. Feng, & J-A. Lee (Eds.), Proceedings of the International MultiConference of Engineers and Computer Scientists 2014 (Vol. 2209, pp. 324-327). (Lecture Notes in Engineering and Computer Science). Hong Kong: Newswood Limited.
HUYNH, Dat ; TRAN, Dat ; MA, Wanli. / Combination Features for Semantic Similarity Measure. Proceedings of the International MultiConference of Engineers and Computer Scientists 2014. editor / S.I Ao ; Oscar Castillo ; Craig Douglas ; David Dagan Feng ; Jeong-A Lee. Vol. 2209 Hong Kong : Newswood Limited, 2014. pp. 324-327 (Lecture Notes in Engineering and Computer Science).
@inproceedings{a12284f078fe4df6bbc88fa2c46e14d3,
title = "Combination Features for Semantic Similarity Measure",
abstract = "Computing the semantic similarity between words is one of the key tasks in many language-based applications. Recent work has focused on using contextual clues for semantic similarity computation. In this paper, we propose a method to the measure semantic similarity between words using plain text contents. It takes into account information attributes (local) and topic information (global) of words to disclose their semantic similarity scores. The method models the representation of a word as a high dimensional vector of word attributes and latent topics. Thus, the semantic similarity between two words is measured by the semantic distance between their respective vectors. We have tested the proposed method on WordSimilarity-353 dataset. The empirical results have shown the combination features contribute to improve the semantic similarity results the dataset in comparison with previous work on the same task using plain text contents.",
keywords = "Semantic Similarity Measure, Natural Language Processing",
author = "Dat HUYNH and Dat TRAN and Wanli MA",
year = "2014",
language = "English",
isbn = "9783319116983",
volume = "2209",
series = "Lecture Notes in Engineering and Computer Science",
publisher = "Newswood Limited",
pages = "324--327",
editor = "S.I Ao and Oscar Castillo and Craig Douglas and Feng, {David Dagan} and Jeong-A Lee",
booktitle = "Proceedings of the International MultiConference of Engineers and Computer Scientists 2014",

}

HUYNH, D, TRAN, D & MA, W 2014, Combination Features for Semantic Similarity Measure. in SI Ao, O Castillo, C Douglas, DD Feng & J-A Lee (eds), Proceedings of the International MultiConference of Engineers and Computer Scientists 2014. vol. 2209, Lecture Notes in Engineering and Computer Science, Newswood Limited, Hong Kong, pp. 324-327, International MultiConference of Engineers and Computer Scientists 2014, Hong Kong, China, 12/03/14.

Combination Features for Semantic Similarity Measure. / HUYNH, Dat; TRAN, Dat; MA, Wanli.

Proceedings of the International MultiConference of Engineers and Computer Scientists 2014. ed. / S.I Ao; Oscar Castillo; Craig Douglas; David Dagan Feng; Jeong-A Lee. Vol. 2209 Hong Kong : Newswood Limited, 2014. p. 324-327 (Lecture Notes in Engineering and Computer Science).

Research output: A Conference proceeding or a Chapter in BookConference contribution

TY - GEN

T1 - Combination Features for Semantic Similarity Measure

AU - HUYNH, Dat

AU - TRAN, Dat

AU - MA, Wanli

PY - 2014

Y1 - 2014

N2 - Computing the semantic similarity between words is one of the key tasks in many language-based applications. Recent work has focused on using contextual clues for semantic similarity computation. In this paper, we propose a method to the measure semantic similarity between words using plain text contents. It takes into account information attributes (local) and topic information (global) of words to disclose their semantic similarity scores. The method models the representation of a word as a high dimensional vector of word attributes and latent topics. Thus, the semantic similarity between two words is measured by the semantic distance between their respective vectors. We have tested the proposed method on WordSimilarity-353 dataset. The empirical results have shown the combination features contribute to improve the semantic similarity results the dataset in comparison with previous work on the same task using plain text contents.

AB - Computing the semantic similarity between words is one of the key tasks in many language-based applications. Recent work has focused on using contextual clues for semantic similarity computation. In this paper, we propose a method to the measure semantic similarity between words using plain text contents. It takes into account information attributes (local) and topic information (global) of words to disclose their semantic similarity scores. The method models the representation of a word as a high dimensional vector of word attributes and latent topics. Thus, the semantic similarity between two words is measured by the semantic distance between their respective vectors. We have tested the proposed method on WordSimilarity-353 dataset. The empirical results have shown the combination features contribute to improve the semantic similarity results the dataset in comparison with previous work on the same task using plain text contents.

KW - Semantic Similarity Measure

KW - Natural Language Processing

UR - http://www.scopus.com/inward/record.url?scp=84901494523&partnerID=8YFLogxK

UR - http://www.iaeng.org/IMECS2014/

M3 - Conference contribution

SN - 9783319116983

VL - 2209

T3 - Lecture Notes in Engineering and Computer Science

SP - 324

EP - 327

BT - Proceedings of the International MultiConference of Engineers and Computer Scientists 2014

A2 - Ao, S.I

A2 - Castillo, Oscar

A2 - Douglas, Craig

A2 - Feng, David Dagan

A2 - Lee, Jeong-A

PB - Newswood Limited

CY - Hong Kong

ER -

HUYNH D, TRAN D, MA W. Combination Features for Semantic Similarity Measure. In Ao SI, Castillo O, Douglas C, Feng DD, Lee J-A, editors, Proceedings of the International MultiConference of Engineers and Computer Scientists 2014. Vol. 2209. Hong Kong: Newswood Limited. 2014. p. 324-327. (Lecture Notes in Engineering and Computer Science).