Word Sense Disambiguation Based on Convolution Neural Network

被引：0
|
作者：
Zhang C.-X. [1 ]
Zhao L.-Y. [2 ]
Gao X.-Y. [2 ]
机构：
[1] School of Software and Microelectronics, Harbin University of Science and Technology, Harbin
[2] School of Computer Science and Technology, Harbin University of Science and Technology, Harbin
来源：
Beijing Youdian Daxue Xuebao/Journal of Beijing University of Posts and Telecommunications | 2019年 / 42卷 / 03期
关键词：
Convolution neural network; Disambiguation features; Semantic categories; Word sense disambiguation;
D O I：
10.13190/j.jbupt.2018-148
中图分类号：
学科分类号：
摘要：
In order to improve the performance of word sense disambiguation (WSD), a disambiguation method based on convolution neural network (CNN) is proposed. Ambiguous word is viewed as center and four adjacent word units around its left and right sides are extended. Word, part-of-speech and semantic categories are extracted as disambiguation features. Based on disambiguation features, CNN is used to determine semantic categories of ambiguous words. Training corpus of SemEval-2007: Task#5 and semantic annotation corpus from Harbin Institute of Technology are used to optimize CNN classifier. Testing corpus of SemEval-2007: Task#5 is used to test the performance of WSD classifier. Average disambiguation accuracy of the proposed method is improved. Experiments show that this method is feasible in WSD. © 2019, Editorial Department of Journal of Beijing University of Posts and Telecommunications. All right reserved.
引用
收藏
页码：114 / 119
页数：5
相关论文
共 17 条
  • [1] Yang Z., Huang H., WSD method based on heterogeneous relation graph, Journal of Computer Research & Development, 50, 2, pp. 437-444, (2013)
  • [2] Koppula N., Rani B.P., Rao K.S., Graph based word sense disambiguation, The 1st International Conference on Computational Intelligence and Informatics, pp. 665-670, (2017)
  • [3] Duque A., Martinezromo J., Araujo L., Can multilinguality improve biomedical word sense disambiguation?, Journal of Biomedical Informatics, 64, 1, pp. 320-332, (2016)
  • [4] Yang A., Li S., Li Y., Word sense disambiguation based on domain knowledge and word vector model, Acta Scientiarum Naturalium Universitatis Pekinensis, 53, 2, pp. 204-210, (2017)
  • [5] Li Y., Huang K., Ren F., Et al., Wikipedia based semantic related Chinese words exploring and relatedness computing, Journal of Beijing University of Posts and Telecommunications, 32, 3, pp. 109-112, (2009)
  • [6] Faisal E., Nurifan F., Sarno R., Word sense disambiguation in Bahasa Indonesia using SVM, International Seminar on Application for Technology of Information and Communication, pp. 239-243, (2018)
  • [7] Wang T., Wang L., Wu J., Et al., Semantic similarity calculation method of comprehensive concept in WordNet, Journal of Beijing University of Posts and Telecommunications, 36, 2, pp. 98-106, (2013)
  • [8] Li Y., Zhai H., Liu F., Et al., Research on word sense disambiguation method based on dependency relation and maximum entropy in Chinese complex sentences, Computer & Digital Engineering, 46, 1, pp. 78-82, (2018)
  • [9] He J., Wang H., Chinese word sense disambiguation based on maximum entropy model with feature selection, Journal of Software, 21, 6, pp. 1287-1295, (2010)
  • [10] Gutierrez Y., Vazquez S., Montoyo A., Spreading semantic information by word sense disambiguation, Knowledge-Based Systems, 132, 1, pp. 47-61, (2017)
12