Recent Research Trends and Proposal of Distributional Word Representations for Hypernymy Detection

Abstract

Distributional representation for words is an important model of word senses which reflects several types of semantic relations, not only similarity relations. In this paper, we provide an overview of unsupervised/supervised approaches with word distributional representations to detect hypernym-hyponym relations and a recently reported problem associated with these approaches. Moreover, we propose a future research direction to solve this problem and prove the validity of this direction with small experiments.