Clustering of Word Contexts as a Method of Eliminating Polysemy of Words

摘要

When processing text documents in natural language, you may encounter such problem as polysemy of words. If the algorithm determines the terms regardless of the semantic component of the words, considering homonymous words as one term, there is a loss of data. As the analysis of the literature data shows, at present no algorithm can unambiguously divide polysemous words into separate terms by semantic groups. In this paper, we propose a method of eliminating polysemy of words, based on the clustering of word contexts, which will improve the quality of processing text documents in natural language.