PolyUCOMP: Combining Semantic Vectors with Skip bigrams for Semantic Textual Similarity

Jian Xu; Qin Lu; Zhengzhong Liu

PolyUCOMP: Combining Semantic Vectors with Skip bigrams for Semantic Textual Similarity

Jian Xu, Qin Lu, Zhengzhong Liu

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

3 Citations (Scopus)

Abstract

This paper presents the work of the Hong Kong Polytechnic University (PolyUCOMP) team which has participated in the Semantic Textual Similarity task of SemEval-2012. The PolyUCOMP system combines semantic vectors with skip bigrams to determine sentence similarity. The semantic vector is used to compute similarities between sentence pairs using the lexical database WordNet and the Wikipedia corpus. The use of skip bigram is to introduce the order of words in measuring sentence similarity.

Original language	English
Title of host publication	Proceedings of the 6th International Workshop on Semantic Evaluation, SemEval 2012
Publisher	Association for Computational Linguistics (ACL)
Pages	524-528
Number of pages	5
Volume	2
ISBN (Electronic)	9781937284220
Publication status	Published - 1 Jan 2012
Event	1st Joint Conference on Lexical and Computational Semantics, *SEM 2012 - Montreal, Canada Duration: 7 Jun 2012 → 8 Jun 2012

Conference

Conference	1st Joint Conference on Lexical and Computational Semantics, *SEM 2012
Country/Territory	Canada
City	Montreal
Period	7/06/12 → 8/06/12

ASJC Scopus subject areas

Computational Theory and Mathematics
Theoretical Computer Science
Computer Science Applications

More information

http://hdl.handle.net/10397/5199

Cite this

@inproceedings{63450bf8bda047f8844e7d89e48ec401,

title = "PolyUCOMP: Combining Semantic Vectors with Skip bigrams for Semantic Textual Similarity",

abstract = "This paper presents the work of the Hong Kong Polytechnic University (PolyUCOMP) team which has participated in the Semantic Textual Similarity task of SemEval-2012. The PolyUCOMP system combines semantic vectors with skip bigrams to determine sentence similarity. The semantic vector is used to compute similarities between sentence pairs using the lexical database WordNet and the Wikipedia corpus. The use of skip bigram is to introduce the order of words in measuring sentence similarity.",

author = "Jian Xu and Qin Lu and Zhengzhong Liu",

year = "2012",

month = jan,

day = "1",

language = "English",

volume = "2",

pages = "524--528",

booktitle = "Proceedings of the 6th International Workshop on Semantic Evaluation, SemEval 2012",

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

note = "1st Joint Conference on Lexical and Computational Semantics, *SEM 2012 ; Conference date: 07-06-2012 Through 08-06-2012",

}

Xu, J, Lu, Q & Liu, Z 2012, PolyUCOMP: Combining Semantic Vectors with Skip bigrams for Semantic Textual Similarity. in Proceedings of the 6th International Workshop on Semantic Evaluation, SemEval 2012. vol. 2, Association for Computational Linguistics (ACL), pp. 524-528, 1st Joint Conference on Lexical and Computational Semantics, *SEM 2012, Montreal, Canada, 7/06/12. <http://hdl.handle.net/10397/5199>

PolyUCOMP: Combining Semantic Vectors with Skip bigrams for Semantic Textual Similarity. / Xu, Jian; Lu, Qin; Liu, Zhengzhong.
Proceedings of the 6th International Workshop on Semantic Evaluation, SemEval 2012. Vol. 2 Association for Computational Linguistics (ACL), 2012. p. 524-528.

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

TY - GEN

T1 - PolyUCOMP: Combining Semantic Vectors with Skip bigrams for Semantic Textual Similarity

AU - Xu, Jian

AU - Lu, Qin

AU - Liu, Zhengzhong

PY - 2012/1/1

Y1 - 2012/1/1

N2 - This paper presents the work of the Hong Kong Polytechnic University (PolyUCOMP) team which has participated in the Semantic Textual Similarity task of SemEval-2012. The PolyUCOMP system combines semantic vectors with skip bigrams to determine sentence similarity. The semantic vector is used to compute similarities between sentence pairs using the lexical database WordNet and the Wikipedia corpus. The use of skip bigram is to introduce the order of words in measuring sentence similarity.

AB - This paper presents the work of the Hong Kong Polytechnic University (PolyUCOMP) team which has participated in the Semantic Textual Similarity task of SemEval-2012. The PolyUCOMP system combines semantic vectors with skip bigrams to determine sentence similarity. The semantic vector is used to compute similarities between sentence pairs using the lexical database WordNet and the Wikipedia corpus. The use of skip bigram is to introduce the order of words in measuring sentence similarity.

UR - http://www.scopus.com/inward/record.url?scp=85041202849&partnerID=8YFLogxK

M3 - Conference article published in proceeding or book

VL - 2

SP - 524

EP - 528

BT - Proceedings of the 6th International Workshop on Semantic Evaluation, SemEval 2012

PB - Association for Computational Linguistics (ACL)

T2 - 1st Joint Conference on Lexical and Computational Semantics, *SEM 2012

Y2 - 7 June 2012 through 8 June 2012

ER -

PolyUCOMP: Combining Semantic Vectors with Skip bigrams for Semantic Textual Similarity

Abstract

Conference

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this