A comparative study of an unsupervised word sense disambiguation approach

Wei Xiong; Min Song; Lori Watrous deDeversterre

doi:10.4018/978-1-60960-741-8.ch024

A comparative study of an unsupervised word sense disambiguation approach

Wei Xiong, Min Song, Lori Watrous deDeversterre

Department of Library and Information Science

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

Abstract

Word sense disambiguation is the problem of selecting a sense for a word from a set of predefined possibilities. This is a significant problem in the biomedical domain where a single word may be used to describe a gene, protein, or abbreviation. In this paper, we evaluate SENSATIONAL, a novel unsupervised WSD technique, in comparison with two popular learning algorithms: support vector machines (SVM) and K-means. Based on the accuracy measure, our results show that SENSATIONAL outperforms SVM and K-means by 2% and 17%, respectively. In addition, we develop a polysemy-based search engine and an experimental visualization application that utilizes SENSATIONAL's clustering technique.

Original language	English
Title of host publication	Applied Natural Language Processing
Subtitle of host publication	Identification, Investigation and Resolution
Publisher	IGI Global
Pages	412-422
Number of pages	11
ISBN (Print)	9781609607418
DOIs	https://doi.org/10.4018/978-1-60960-741-8.ch024
Publication status	Published - 2011 Dec 1

Fingerprint

All Science Journal Classification (ASJC) codes

Computer Science(all)

Cite this

Xiong, W., Song, M., & deDeversterre, L. W. (2011). A comparative study of an unsupervised word sense disambiguation approach. In Applied Natural Language Processing: Identification, Investigation and Resolution (pp. 412-422). IGI Global. https://doi.org/10.4018/978-1-60960-741-8.ch024

@inbook{78e01fd327b54f32a31f3704f8f87749,

title = "A comparative study of an unsupervised word sense disambiguation approach",

abstract = "Word sense disambiguation is the problem of selecting a sense for a word from a set of predefined possibilities. This is a significant problem in the biomedical domain where a single word may be used to describe a gene, protein, or abbreviation. In this paper, we evaluate SENSATIONAL, a novel unsupervised WSD technique, in comparison with two popular learning algorithms: support vector machines (SVM) and K-means. Based on the accuracy measure, our results show that SENSATIONAL outperforms SVM and K-means by 2% and 17%, respectively. In addition, we develop a polysemy-based search engine and an experimental visualization application that utilizes SENSATIONAL's clustering technique.",

author = "Wei Xiong and Min Song and deDeversterre, {Lori Watrous}",

year = "2011",

month = dec

day = "1",

doi = "10.4018/978-1-60960-741-8.ch024",

language = "English",

isbn = "9781609607418",

pages = "412--422",

booktitle = "Applied Natural Language Processing",

publisher = "IGI Global",

}

TY - CHAP

T1 - A comparative study of an unsupervised word sense disambiguation approach

AU - Xiong, Wei

AU - Song, Min

AU - deDeversterre, Lori Watrous

PY - 2011/12/1

Y1 - 2011/12/1

N2 - Word sense disambiguation is the problem of selecting a sense for a word from a set of predefined possibilities. This is a significant problem in the biomedical domain where a single word may be used to describe a gene, protein, or abbreviation. In this paper, we evaluate SENSATIONAL, a novel unsupervised WSD technique, in comparison with two popular learning algorithms: support vector machines (SVM) and K-means. Based on the accuracy measure, our results show that SENSATIONAL outperforms SVM and K-means by 2% and 17%, respectively. In addition, we develop a polysemy-based search engine and an experimental visualization application that utilizes SENSATIONAL's clustering technique.

AB - Word sense disambiguation is the problem of selecting a sense for a word from a set of predefined possibilities. This is a significant problem in the biomedical domain where a single word may be used to describe a gene, protein, or abbreviation. In this paper, we evaluate SENSATIONAL, a novel unsupervised WSD technique, in comparison with two popular learning algorithms: support vector machines (SVM) and K-means. Based on the accuracy measure, our results show that SENSATIONAL outperforms SVM and K-means by 2% and 17%, respectively. In addition, we develop a polysemy-based search engine and an experimental visualization application that utilizes SENSATIONAL's clustering technique.

UR - http://www.scopus.com/inward/record.url?scp=84899252465&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84899252465&partnerID=8YFLogxK

U2 - 10.4018/978-1-60960-741-8.ch024

DO - 10.4018/978-1-60960-741-8.ch024

M3 - Chapter

AN - SCOPUS:84899252465

SN - 9781609607418

SP - 412

EP - 422

BT - Applied Natural Language Processing

PB - IGI Global

ER -

Access to Document

10.4018/978-1-60960-741-8.ch024