文章基本信息

标题：TWE‐WSD: An effective topical word embedding based word sense disambiguation
本地全文：下载
作者：Lianyin Jia ; Jilin Tang ; Mengjuan Li 等
期刊名称：CAAI Transactions on Intelligence Technology
电子版ISSN：2468-2322
出版年度：2021
卷号：6
期号：1
页码：72-79
DOI：10.1049/cit2.12006
出版社：IET Digital Library
摘要：Word embedding has been widely used in word sense disambiguation (WSD) and many other tasks in recent years for it can well represent the semantics of words. However, the existing word embedding methods mostly represent each word as a single vector, without considering the homonymy and polysemy of the word; thus, their performances are limited. In order to address this problem, an effective topical word embedding (TWE)‐based WSD method, named TWE‐WSD, is proposed, which integrates Latent Dirichlet Allocation (LDA) andword embedding.Instead of generating a singleword vector(WV)for eachword, TWE‐WSD generates a topical WV for each word under each topic. Effective integrating strategies are designed to obtain high quality contextual vectors. Extensive experiments on SemEval‐2013 and SemEval‐2015 for English all‐words tasks showed that TWE‐WSD outperforms other state‐of‐the‐art WSD methods, especially on nouns.