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 ProceedingsConference paper (refereed)Research


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 languageEnglish
Title of host publicationWeb Information Systems Engineering – WISE 2017 : 18th International Conference, Puschino, Russia, October 7-11, 2017, proceedings, part II
EditorsAthman BOUGUETTAYA, Yunjun GAO, Andrey KLIMENKO, Lu CHEN, Xiangliang ZHANG, Fedor DZERZHINSKIY, Weijia JIA, Stanislav V. KLIMENKO, Qing LI
PublisherSpringer International Publishing AG
Number of pages15
ISBN (Electronic)9783319687865
ISBN (Print)9783319687858
Publication statusPublished - 2017
Externally publishedYes
Event18th International Conference on Web Information Systems Engineering - Hotel “TsarGrad”, Moscow, Russian Federation
Duration: 7 Oct 201711 Oct 2017

Publication series

NameLecture Notes in Computer Science
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349


Conference18th International Conference on Web Information Systems Engineering
Abbreviated titleWISE 2017
Country/TerritoryRussian Federation
Internet address

Bibliographical note

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).


  • Word sense disambiguation
  • Word embeddings
  • Natural language processing


Dive into the research topics of 'Combining local and global features in supervised word sense disambiguation'. Together they form a unique fingerprint.

Cite this