Combining local and global features in supervised word sense disambiguation

Xue LEI; Yi CAI; Qing LI; Haoran XIE; Ho-fung  LEUNG; Fu Lee WANG

doi:10.1007/978-3-319-68786-5_10

Combining local and global features in supervised word sense disambiguation

Xue LEI, Yi CAI, Qing LI, Haoran XIE, Ho-fung LEUNG, Fu Lee WANG

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Research

Abstract

Word Sense Disambiguation (WSD) is a task to identify the sense of a polysemy in given context. Recently, word embeddings are applied to WSD, as additional input features of a supervised classifier. However, previous approaches narrowly use word embeddings to represent surrounding words of target words. They may not make sufficient use of word embeddings in representing different features like dependency relations, word order and global contexts (the whole document). In this work, we combine local and global features to perform WSD. We explore utilizing word embeddings to leverage word order and dependency features. We also use word embeddings to represent global contexts as global features. We conduct experiments to evaluate our methods and find out that our methods outperform the state-of-the-art methods on Lexical Sample WSD datasets.

Original language	English
Title of host publication	Web Information Systems Engineering – WISE 2017 : 18th International Conference, Puschino, Russia, October 7-11, 2017, proceedings, part II
Editors	Athman BOUGUETTAYA, Yunjun GAO, Andrey KLIMENKO, Lu CHEN, Xiangliang ZHANG, Fedor DZERZHINSKIY, Weijia JIA, Stanislav V. KLIMENKO, Qing LI
Publisher	Springer International Publishing AG
Pages	117-131
Number of pages	15
ISBN (Electronic)	9783319687865
ISBN (Print)	9783319687858
DOIs	https://doi.org/10.1007/978-3-319-68786-5_10
Publication status	Published - 2017
Externally published	Yes
Event	18th International Conference on Web Information Systems Engineering - Hotel “TsarGrad”, Moscow, Russian Federation Duration: 7 Oct 2017 → 11 Oct 2017 http://www.wise-conferences.org/2017/index.html

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer
Volume	10570
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	18th International Conference on Web Information Systems Engineering
Abbreviated title	WISE 2017
Country/Territory	Russian Federation
City	Moscow
Period	7/10/17 → 11/10/17
Internet address	http://www.wise-conferences.org/2017/index.html

Bibliographical note

Publisher Copyright:
© 2017, Springer International Publishing AG.

Funding

This work is supported by the Fundamental Research Funds for the Central Universities, SCUT (Nos. 2017ZD048, 2015ZM136), Tiptop Scientific and Technical Innovative Youth Talents of Guangdong special support program (No. 2015TQ01X633), Science and Technology Planning Project of Guangdong Province, China (No. 2016A030310423), Science and Technology Program of Guangzhou (International Science & Technology Cooperation Program No. 201704030076) and Science and Technology Planning Major Project of Guangdong Province (No. 2015A070711001), the Start-Up Research Grant (RG 37/2016-2017R), and a grant from Research Grants Council of Hong Kong Special Administrative Region, China (UGC/FDS11/E03/16). This work is also partially supported by a CUHK Direct Grant for Research (Project Code EE16963).

Keywords

Word sense disambiguation
Word embeddings
Natural language processing

Access to Document

10.1007/978-3-319-68786-5_10

Cite this

LEI, X., CAI, Y., LI, Q., XIE, H., LEUNG, H., & WANG, F. L. (2017). Combining local and global features in supervised word sense disambiguation. In A. BOUGUETTAYA, Y. GAO, A. KLIMENKO, L. CHEN, X. ZHANG, F. DZERZHINSKIY, W. JIA, S. V. KLIMENKO, & Q. LI (Eds.), Web Information Systems Engineering – WISE 2017 : 18th International Conference, Puschino, Russia, October 7-11, 2017, proceedings, part II (pp. 117-131). (Lecture Notes in Computer Science; Vol. 10570). Springer International Publishing AG. https://doi.org/10.1007/978-3-319-68786-5_10

LEI, Xue ; CAI, Yi ; LI, Qing et al. / Combining local and global features in supervised word sense disambiguation. Web Information Systems Engineering – WISE 2017 : 18th International Conference, Puschino, Russia, October 7-11, 2017, proceedings, part II. editor / Athman BOUGUETTAYA ; Yunjun GAO ; Andrey KLIMENKO ; Lu CHEN ; Xiangliang ZHANG ; Fedor DZERZHINSKIY ; Weijia JIA ; Stanislav V. KLIMENKO ; Qing LI. Springer International Publishing AG, 2017. pp. 117-131 (Lecture Notes in Computer Science).

@inproceedings{24960311faa64e669af30b06ac4f8f4e,

title = "Combining local and global features in supervised word sense disambiguation",

abstract = "Word Sense Disambiguation (WSD) is a task to identify the sense of a polysemy in given context. Recently, word embeddings are applied to WSD, as additional input features of a supervised classifier. However, previous approaches narrowly use word embeddings to represent surrounding words of target words. They may not make sufficient use of word embeddings in representing different features like dependency relations, word order and global contexts (the whole document). In this work, we combine local and global features to perform WSD. We explore utilizing word embeddings to leverage word order and dependency features. We also use word embeddings to represent global contexts as global features. We conduct experiments to evaluate our methods and find out that our methods outperform the state-of-the-art methods on Lexical Sample WSD datasets.",

keywords = "Word sense disambiguation, Word embeddings, Natural language processing",

author = "Xue LEI and Yi CAI and Qing LI and Haoran XIE and Ho-fung LEUNG and WANG, {Fu Lee}",

note = "Publisher Copyright: {\textcopyright} 2017, Springer International Publishing AG.; 18th International Conference on Web Information Systems Engineering, WISE 2017 ; Conference date: 07-10-2017 Through 11-10-2017",

year = "2017",

doi = "10.1007/978-3-319-68786-5_10",

language = "English",

isbn = "9783319687858",

series = "Lecture Notes in Computer Science",

publisher = "Springer International Publishing AG",

pages = "117--131",

editor = "Athman BOUGUETTAYA and GAO, {Yunjun } and Andrey KLIMENKO and Lu CHEN and Xiangliang ZHANG and Fedor DZERZHINSKIY and JIA, {Weijia } and KLIMENKO, {Stanislav V.} and Qing LI",

booktitle = "Web Information Systems Engineering – WISE 2017 : 18th International Conference, Puschino, Russia, October 7-11, 2017, proceedings, part II",

address = "Switzerland",

url = "http://www.wise-conferences.org/2017/index.html",

}

LEI, X, CAI, Y, LI, Q, XIE, H, LEUNG, H & WANG, FL 2017, Combining local and global features in supervised word sense disambiguation. in A BOUGUETTAYA, Y GAO, A KLIMENKO, L CHEN, X ZHANG, F DZERZHINSKIY, W JIA, SV KLIMENKO & Q LI (eds), Web Information Systems Engineering – WISE 2017 : 18th International Conference, Puschino, Russia, October 7-11, 2017, proceedings, part II. Lecture Notes in Computer Science, vol. 10570, Springer International Publishing AG, pp. 117-131, 18th International Conference on Web Information Systems Engineering, Moscow, Russian Federation, 7/10/17. https://doi.org/10.1007/978-3-319-68786-5_10

Combining local and global features in supervised word sense disambiguation. / LEI, Xue; CAI, Yi; LI, Qing et al.
Web Information Systems Engineering – WISE 2017 : 18th International Conference, Puschino, Russia, October 7-11, 2017, proceedings, part II. ed. / Athman BOUGUETTAYA; Yunjun GAO; Andrey KLIMENKO; Lu CHEN; Xiangliang ZHANG; Fedor DZERZHINSKIY; Weijia JIA; Stanislav V. KLIMENKO; Qing LI. Springer International Publishing AG, 2017. p. 117-131 (Lecture Notes in Computer Science; Vol. 10570).

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Research

TY - GEN

T1 - Combining local and global features in supervised word sense disambiguation

AU - LEI, Xue

AU - CAI, Yi

AU - LI, Qing

AU - XIE, Haoran

AU - LEUNG, Ho-fung

AU - WANG, Fu Lee

PY - 2017

Y1 - 2017

N2 - Word Sense Disambiguation (WSD) is a task to identify the sense of a polysemy in given context. Recently, word embeddings are applied to WSD, as additional input features of a supervised classifier. However, previous approaches narrowly use word embeddings to represent surrounding words of target words. They may not make sufficient use of word embeddings in representing different features like dependency relations, word order and global contexts (the whole document). In this work, we combine local and global features to perform WSD. We explore utilizing word embeddings to leverage word order and dependency features. We also use word embeddings to represent global contexts as global features. We conduct experiments to evaluate our methods and find out that our methods outperform the state-of-the-art methods on Lexical Sample WSD datasets.

AB - Word Sense Disambiguation (WSD) is a task to identify the sense of a polysemy in given context. Recently, word embeddings are applied to WSD, as additional input features of a supervised classifier. However, previous approaches narrowly use word embeddings to represent surrounding words of target words. They may not make sufficient use of word embeddings in representing different features like dependency relations, word order and global contexts (the whole document). In this work, we combine local and global features to perform WSD. We explore utilizing word embeddings to leverage word order and dependency features. We also use word embeddings to represent global contexts as global features. We conduct experiments to evaluate our methods and find out that our methods outperform the state-of-the-art methods on Lexical Sample WSD datasets.

KW - Word sense disambiguation

KW - Word embeddings

KW - Natural language processing

UR - http://www.scopus.com/inward/record.url?scp=85031396707&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-68786-5_10

DO - 10.1007/978-3-319-68786-5_10

M3 - Conference paper (refereed)

SN - 9783319687858

T3 - Lecture Notes in Computer Science

SP - 117

EP - 131

BT - Web Information Systems Engineering – WISE 2017 : 18th International Conference, Puschino, Russia, October 7-11, 2017, proceedings, part II

A2 - BOUGUETTAYA, Athman

A2 - GAO, Yunjun

A2 - KLIMENKO, Andrey

A2 - CHEN, Lu

A2 - ZHANG, Xiangliang

A2 - DZERZHINSKIY, Fedor

A2 - JIA, Weijia

A2 - KLIMENKO, Stanislav V.

A2 - LI, Qing

PB - Springer International Publishing AG

T2 - 18th International Conference on Web Information Systems Engineering

Y2 - 7 October 2017 through 11 October 2017

ER -

LEI X, CAI Y, LI Q, XIE H, LEUNG H, WANG FL. Combining local and global features in supervised word sense disambiguation. In BOUGUETTAYA A, GAO Y, KLIMENKO A, CHEN L, ZHANG X, DZERZHINSKIY F, JIA W, KLIMENKO SV, LI Q, editors, Web Information Systems Engineering – WISE 2017 : 18th International Conference, Puschino, Russia, October 7-11, 2017, proceedings, part II. Springer International Publishing AG. 2017. p. 117-131. (Lecture Notes in Computer Science). Epub 2017 Oct 4. doi: 10.1007/978-3-319-68786-5_10

Combining local and global features in supervised word sense disambiguation

Abstract

Publication series

Conference

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this