PolyUCOMP-CORE TYPED: Computing Semantic Textual Similarity using Overlapped Senses

Jian Xu; Qin Lu

PolyUCOMP-CORE TYPED: Computing Semantic Textual Similarity using Overlapped Senses

Jian Xu, Qin Lu

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

1 Citation (Scopus)

Abstract

c 2013 Association for Computational Linguistics The Semantic Textual Similarity (STS) task aims to exam the degree of semantic equivalence between sentences (Agirre et al., 2012). This paper presents the work of the Hong Kong Polytechnic University (PolyUCOMP) team which has participated in the STS core and typed tasks of SemEval-2013. For the STS core task, the PolyUCOMP system disambiguates words senses using contexts and then determine sentence similarity by counting the number of senses they shared. For the STS typed task, the string kernel (Lodhi et al., 2002) is used to compute similarity between two entities to avoid string variations in entities.

Original language	English
Title of host publication	*SEM 2013 - 2nd Joint Conference on Lexical and Computational Semantics
Publisher	Association for Computational Linguistics (ACL)
Pages	90-95
Number of pages	6
Volume	1
ISBN (Electronic)	9781937284480
Publication status	Published - 1 Jan 2013
Event	2nd Joint Conference on Lexical and Computational Semantics, *SEM 2013 - Atlanta, United States Duration: 13 Jun 2013 → 14 Jun 2013

Conference

Conference	2nd Joint Conference on Lexical and Computational Semantics, *SEM 2013
Country/Territory	United States
City	Atlanta
Period	13/06/13 → 14/06/13

ASJC Scopus subject areas

Computational Theory and Mathematics
Computer Science Applications
Theoretical Computer Science

Cite this

@inproceedings{6ef55f7bbfec47a5ac76808f3f0d936f,

title = "PolyUCOMP-CORE TYPED: Computing Semantic Textual Similarity using Overlapped Senses",

abstract = "c 2013 Association for Computational Linguistics The Semantic Textual Similarity (STS) task aims to exam the degree of semantic equivalence between sentences (Agirre et al., 2012). This paper presents the work of the Hong Kong Polytechnic University (PolyUCOMP) team which has participated in the STS core and typed tasks of SemEval-2013. For the STS core task, the PolyUCOMP system disambiguates words senses using contexts and then determine sentence similarity by counting the number of senses they shared. For the STS typed task, the string kernel (Lodhi et al., 2002) is used to compute similarity between two entities to avoid string variations in entities.",

author = "Jian Xu and Qin Lu",

year = "2013",

month = jan,

day = "1",

language = "English",

volume = "1",

pages = "90--95",

booktitle = "*SEM 2013 - 2nd Joint Conference on Lexical and Computational Semantics",

publisher = "Association for Computational Linguistics (ACL)",

note = "2nd Joint Conference on Lexical and Computational Semantics, *SEM 2013 ; Conference date: 13-06-2013 Through 14-06-2013",

}

PolyUCOMP-CORE TYPED: Computing Semantic Textual Similarity using Overlapped Senses. / Xu, Jian; Lu, Qin.
*SEM 2013 - 2nd Joint Conference on Lexical and Computational Semantics. Vol. 1 Association for Computational Linguistics (ACL), 2013. p. 90-95.

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - PolyUCOMP-CORE TYPED: Computing Semantic Textual Similarity using Overlapped Senses

AU - Xu, Jian

AU - Lu, Qin

PY - 2013/1/1

Y1 - 2013/1/1

N2 - c 2013 Association for Computational Linguistics The Semantic Textual Similarity (STS) task aims to exam the degree of semantic equivalence between sentences (Agirre et al., 2012). This paper presents the work of the Hong Kong Polytechnic University (PolyUCOMP) team which has participated in the STS core and typed tasks of SemEval-2013. For the STS core task, the PolyUCOMP system disambiguates words senses using contexts and then determine sentence similarity by counting the number of senses they shared. For the STS typed task, the string kernel (Lodhi et al., 2002) is used to compute similarity between two entities to avoid string variations in entities.

AB - c 2013 Association for Computational Linguistics The Semantic Textual Similarity (STS) task aims to exam the degree of semantic equivalence between sentences (Agirre et al., 2012). This paper presents the work of the Hong Kong Polytechnic University (PolyUCOMP) team which has participated in the STS core and typed tasks of SemEval-2013. For the STS core task, the PolyUCOMP system disambiguates words senses using contexts and then determine sentence similarity by counting the number of senses they shared. For the STS typed task, the string kernel (Lodhi et al., 2002) is used to compute similarity between two entities to avoid string variations in entities.

UR - http://www.scopus.com/inward/record.url?scp=85040630971&partnerID=8YFLogxK

M3 - Conference article published in proceeding or book

VL - 1

SP - 90

EP - 95

BT - *SEM 2013 - 2nd Joint Conference on Lexical and Computational Semantics

PB - Association for Computational Linguistics (ACL)

T2 - 2nd Joint Conference on Lexical and Computational Semantics, *SEM 2013

Y2 - 13 June 2013 through 14 June 2013

ER -

PolyUCOMP-CORE TYPED: Computing Semantic Textual Similarity using Overlapped Senses

Abstract

Conference

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this