Directional Distributional Similarity for Lexical Expansion
Lili Kotlerman, Ido Dagan, Idan Szpektor and Maayan Geffet
Proceedings of the ACL-IJCNLP 2009 Conference Short Papers
Distributional word similarity is most
commonly perceived as a symmetric relation.
Yet, one of its major applications
is lexical expansion, which is generally
asymmetric. This paper investigates the
nature of directional (asymmetric) similarity
measures, which aim to quantify distributional
feature inclusion. We identify desired
properties of such measures, specify
a particular one based on averaged precision,
and demonstrate the empirical benefit
of directional measures for expansion.