MayoClinicNLP–CORE: Semantic representations for textual similarity

Stephen Wu; Dongqing Zhu; Ben Carterette; Hongfang Liu

MayoClinicNLP–CORE: Semantic representations for textual similarity

Stephen Wu, Dongqing Zhu, Ben Carterette, Hongfang Liu

Digital Health Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

4 Scopus citations

Abstract

The Semantic Textual Similarity (STS) task examines semantic similarity at a sentence-level. We explored three representations of semantics (implicit or explicit): named entities, semantic vectors, and structured vectorial semantics. From a DKPro baseline, we also performed feature selection and used source-specific linear regression models to combine our features. Our systems placed 5th, 6th, and 8th among 90 submitted systems.

Original language	English (US)
Title of host publication	*SEM 2013 - 2nd Joint Conference on Lexical and Computational Semantics
Publisher	Association for Computational Linguistics (ACL)
Pages	148-154
Number of pages	7
ISBN (Electronic)	9781937284480
State	Published - 2013
Event	2nd Joint Conference on Lexical and Computational Semantics, *SEM 2013 - Atlanta, United States Duration: Jun 13 2013 → Jun 14 2013

Publication series

Name	*SEM 2013 - 2nd Joint Conference on Lexical and Computational Semantics
Volume	1

Other

Other	2nd Joint Conference on Lexical and Computational Semantics, *SEM 2013
Country/Territory	United States
City	Atlanta
Period	6/13/13 → 6/14/13

ASJC Scopus subject areas

Computational Theory and Mathematics
Computer Science Applications
Theoretical Computer Science

Cite this

MayoClinicNLP–CORE: Semantic representations for textual similarity. / Wu, Stephen; Zhu, Dongqing; Carterette, Ben et al.
*SEM 2013 - 2nd Joint Conference on Lexical and Computational Semantics. Association for Computational Linguistics (ACL), 2013. p. 148-154 (*SEM 2013 - 2nd Joint Conference on Lexical and Computational Semantics; Vol. 1).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Wu, S, Zhu, D, Carterette, B & Liu, H 2013, MayoClinicNLP–CORE: Semantic representations for textual similarity. in *SEM 2013 - 2nd Joint Conference on Lexical and Computational Semantics. *SEM 2013 - 2nd Joint Conference on Lexical and Computational Semantics, vol. 1, Association for Computational Linguistics (ACL), pp. 148-154, 2nd Joint Conference on Lexical and Computational Semantics, *SEM 2013, Atlanta, United States, 6/13/13.

@inproceedings{52ed00683a8a43b3a5554ae216d2e0ee,

title = "MayoClinicNLP–CORE: Semantic representations for textual similarity",

abstract = "The Semantic Textual Similarity (STS) task examines semantic similarity at a sentence-level. We explored three representations of semantics (implicit or explicit): named entities, semantic vectors, and structured vectorial semantics. From a DKPro baseline, we also performed feature selection and used source-specific linear regression models to combine our features. Our systems placed 5th, 6th, and 8th among 90 submitted systems.",

author = "Stephen Wu and Dongqing Zhu and Ben Carterette and Hongfang Liu",

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

year = "2013",

language = "English (US)",

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

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

pages = "148--154",

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

}

TY - GEN

T1 - MayoClinicNLP–CORE

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

AU - Wu, Stephen

AU - Zhu, Dongqing

AU - Carterette, Ben

AU - Liu, Hongfang

PY - 2013

Y1 - 2013

N2 - The Semantic Textual Similarity (STS) task examines semantic similarity at a sentence-level. We explored three representations of semantics (implicit or explicit): named entities, semantic vectors, and structured vectorial semantics. From a DKPro baseline, we also performed feature selection and used source-specific linear regression models to combine our features. Our systems placed 5th, 6th, and 8th among 90 submitted systems.

AB - The Semantic Textual Similarity (STS) task examines semantic similarity at a sentence-level. We explored three representations of semantics (implicit or explicit): named entities, semantic vectors, and structured vectorial semantics. From a DKPro baseline, we also performed feature selection and used source-specific linear regression models to combine our features. Our systems placed 5th, 6th, and 8th among 90 submitted systems.

UR - http://www.scopus.com/inward/record.url?scp=84958230417&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84958230417&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84958230417

T3 - *SEM 2013 - 2nd Joint Conference on Lexical and Computational Semantics

SP - 148

EP - 154

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

PB - Association for Computational Linguistics (ACL)

Y2 - 13 June 2013 through 14 June 2013

ER -

MayoClinicNLP–CORE: Semantic representations for textual similarity

Abstract

Publication series

Other

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this