Publication at Faculty of Mathematics and Physics |
2020
Abstract
Word association is an important part of human language. Many techniques for capturing semantic relations between words exist, but their ability to model word associations is rarely tested in a real application.
In this paper, we evaluate three models aimed at different types of word associations: a word-embedding model for synonymy, a point-wise mutual information model for word collocations, and a dependency model for common properties of words. The quality of the proposed models is tested on English and Czech by humans in an online version of the word-association game "Codenames".