Identifying hypernyms in distributional semantic spaces
127 Citations•2023•
Alessandro Lenci, Giulia Benotto
This paper applies existing directional similarity measures to identify hypernyms with a state-of-the-art distributional semantic model and proposes a new directional measure that achieves the best performance in hypernym identification.
Abstract
In this paper we apply existing directional similarity measures to identify hypernyms with a state-of-the-art distributional semantic model. We also propose a new directional measure that achieves the best performance in hypernym identification.