Home // SEMAPRO 2020, The Fourteenth International Conference on Advances in Semantic Processing // View article

Word Sense Disambiguation Using Graph-based Semi-supervised Learning

Authors:
Rie Yatabe
Minoru Sasaki

Keywords: word sense disambiguation; graph convolutional neural network; semi-supervised learning

Abstract:
Word Sense Disambiguation (WSD) is a well-known problem in the natural language processing. In recent years, there has been increasing interest in applying neural networks and machine learning techniques to solve WSD problems. However, these previous approaches often suffer from the lack of manually sense-tagged examples. Moreover, most supervised WSD methods suffer from small differences of examples within the overall training data or within each of the two sense labels. In this paper, to solve these problems, we propose a semi-supervised WSD method using graph convolutional neural network and investigate what kind of features are effective for this model. Experimental results show that the proposed method performs better than the previous supervised method and the morphological features obtained by the UniDic short-unit dictionary is effective for the semi-supervised WSD method. Moreover, the Jaccard coefficient is the most effective measure among three measures to construct a graph structure.

Pages: 1 to 6

Copyright: Copyright (c) IARIA, 2020

Publication date: October 25, 2020

Published in: conference

ISSN: 2308-4510

ISBN: 978-1-61208-813-6

Location: Nice, France

Dates: from October 25, 2020 to October 29, 2020