Statistical Thesaurus Construction for a Morphologically Rich Language
Chaya Liebeskind, Ido Dagan, Jonathan Schler · 2012
Corpus-based thesaurus construction for Morphologically Rich Languages (MRL) is a complex task, due to the morphological variability of MRL. In this paper we explore alternative term representations, complemented by clustering of morphological variants. We introduce a generic algorithmic scheme for thesaurus construction in MRL, and demonstrate the empirical benefit of our methodology for a Hebrew thesaurus.