Word Sense Disambiguation Based on Center Window

Author:

Zhang Chun Xiang1,Guo Li Li1,Gao Xue Yao2

Affiliation:

1. Harbin Engineering University

2. Harbin University of Science and Technology

Abstract

Word sense disambiguation is widely applied to information retrieval, semantic comprehension and automatic summarization. It is an important research problem in natural language processing. In this paper, the center window is determined from the target ambiguous word. The words in the center window are extracted as discriminative features. At the same time, a new method of word sense disambiguation is proposed and the disambiguation classifier is given. The classifier is optimized and tested on SemEval-2007 #Task5 corpus. Experimental results show that the accuracy rate of disambiguation arrives at 64.2%.

Publisher

Trans Tech Publications, Ltd.

Subject

General Engineering

Reference10 articles.

1. Tinghua Wang, Junyang Rao and Dongyan Zhao. Using exponential kernel for word sense disambiguation. In Proceedings of the 23rd International Conference on Artificial Neural Networks. 2013: 545~552.

2. Ariel Raviv and Shaul Markovitch. Concept-based approach to word-sense disambiguation. In Proceedings of the 26th AAAI Conference on Artificial Intelligence and the 24th Innovative Applications of Artificial Intelligence Conference. 2012: 807~813.

3. Ioana Hulpus and Conor Hayes. An eigenvalue-based measure for word-sense disambiguation. In Proceedings of the 25th International Florida Artificial Intelligence Research Society Conference. 2012: 226~231.

4. Xu Li, Xiuyan Zhao and Fenglong Fan. An improved unsupervised learning probabilistic model of word sense disambiguation. In Proceedings of the 2012 World Congress on Information and Communication Technologies. 2012: 1071~1075.

5. Cem Akkaya, Janyce Wiebe and Rada Mihalcea. Utilizing semantic composition in distributional semantic models for word sense discrimination and word sense disambiguation. In Proceedings of IEEE 6th International Conference on Semantic Computing. 2012: 45~51.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3