An Empirical Study of Classifier Combination Based Word Sense Disambiguation

Wenpeng LU; Hao WU; Ping JIAN; Yonggang HUANG; Heyan HUANG

doi:10.1587/transinf.2017EDP7090

An Empirical Study of Classifier Combination Based Word Sense Disambiguation

Wenpeng LU, Hao WU, Ping JIAN, Yonggang HUANG, Heyan HUANG

Full Text Views

0

Cite this

Summary :

Word sense disambiguation (WSD) is to identify the right sense of ambiguous words via mining their context information. Previous studies show that classifier combination is an effective approach to enhance the performance of WSD. In this paper, we systematically review state-of-the-art methods for classifier combination based WSD, including probability-based and voting-based approaches. Furthermore, a new classifier combination based WSD, namely the probability weighted voting method with dynamic self-adaptation, is proposed in this paper. Compared with existing approaches, the new method can take into consideration both the differences of classifiers and ambiguous instances. Exhaustive experiments are performed on a real-world dataset, the results show the superiority of our method over state-of-the-art methods.

Publication: IEICE TRANSACTIONS on Information Vol.E101-D No.1 pp.225-233

Publication Date: 2018/01/01

Publicized: 2017/08/23

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2017EDP7090

Type of Manuscript: PAPER

Category: Natural Language Processing

Authors

Wenpeng LU
  Qilu University of Technology (Shandong Academy of Sciences)
Hao WU
  Beijing Institute of Technology
Ping JIAN
  Beijing Institute of Technology
Yonggang HUANG
  Beijing Institute of Technology
Heyan HUANG
  Beijing Institute of Technology

Keyword

word sense disambiguation, classifier combination, probability weighted voting method, self-adaptation

Cite this

Copy

Wenpeng LU, Hao WU, Ping JIAN, Yonggang HUANG, Heyan HUANG, "An Empirical Study of Classifier Combination Based Word Sense Disambiguation" in IEICE TRANSACTIONS on Information, vol. E101-D, no. 1, pp. 225-233, January 2018, doi: 10.1587/transinf.2017EDP7090.
Abstract: Word sense disambiguation (WSD) is to identify the right sense of ambiguous words via mining their context information. Previous studies show that classifier combination is an effective approach to enhance the performance of WSD. In this paper, we systematically review state-of-the-art methods for classifier combination based WSD, including probability-based and voting-based approaches. Furthermore, a new classifier combination based WSD, namely the probability weighted voting method with dynamic self-adaptation, is proposed in this paper. Compared with existing approaches, the new method can take into consideration both the differences of classifiers and ambiguous instances. Exhaustive experiments are performed on a real-world dataset, the results show the superiority of our method over state-of-the-art methods.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2017EDP7090/_p

Copy

@ARTICLE{e101-d_1_225,
author={Wenpeng LU, Hao WU, Ping JIAN, Yonggang HUANG, Heyan HUANG, },
journal={IEICE TRANSACTIONS on Information},
title={An Empirical Study of Classifier Combination Based Word Sense Disambiguation},
year={2018},
volume={E101-D},
number={1},
pages={225-233},
abstract={Word sense disambiguation (WSD) is to identify the right sense of ambiguous words via mining their context information. Previous studies show that classifier combination is an effective approach to enhance the performance of WSD. In this paper, we systematically review state-of-the-art methods for classifier combination based WSD, including probability-based and voting-based approaches. Furthermore, a new classifier combination based WSD, namely the probability weighted voting method with dynamic self-adaptation, is proposed in this paper. Compared with existing approaches, the new method can take into consideration both the differences of classifiers and ambiguous instances. Exhaustive experiments are performed on a real-world dataset, the results show the superiority of our method over state-of-the-art methods.},
keywords={},
doi={10.1587/transinf.2017EDP7090},
ISSN={1745-1361},
month={January},}

Copy

TY - JOUR
TI - An Empirical Study of Classifier Combination Based Word Sense Disambiguation
T2 - IEICE TRANSACTIONS on Information
SP - 225
EP - 233
AU - Wenpeng LU
AU - Hao WU
AU - Ping JIAN
AU - Yonggang HUANG
AU - Heyan HUANG
PY - 2018
DO - 10.1587/transinf.2017EDP7090
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E101-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 2018
AB - Word sense disambiguation (WSD) is to identify the right sense of ambiguous words via mining their context information. Previous studies show that classifier combination is an effective approach to enhance the performance of WSD. In this paper, we systematically review state-of-the-art methods for classifier combination based WSD, including probability-based and voting-based approaches. Furthermore, a new classifier combination based WSD, namely the probability weighted voting method with dynamic self-adaptation, is proposed in this paper. Compared with existing approaches, the new method can take into consideration both the differences of classifiers and ambiguous instances. Exhaustive experiments are performed on a real-world dataset, the results show the superiority of our method over state-of-the-art methods.
ER -