Multilingual Reliability and "Semantic" Structure of Continuous Word Spaces
Maximilian Köper, Christian Scheible, Sabine Schulte im Walde · 2015
While continuous word vector representations enjoy increasing popularity, it is still poorly understood (i) how reliable they are for other languages than English, and (ii) to what extent they encode deep semantic relatedness such as paradigmatic relations. This study presents experiments with continuous word vectors for English and German, a morphologically rich language. For evaluation, we use both published and newly created datasets of morpho-syntactic and semantic relations. Our results show that (i) morphological complexity causes a drop in accuracy, and (ii) continuous representations lack the ability to solve analogies of paradigmatic relations.