Modeling the Statistical Idiosyncrasy of Multiword Expressions

The focus of this work is statistical idiosyncrasy (or collocational weight) as a discriminant property of multiword expressions. We formalize and model this property, compile a 2-class data set of MWE and non-MWE examples, and evaluate our models on this data set. We present a possible empirical implementation of collocational weight and study its effects on identification and extraction of MWEs. Our models prove to be more effective than baselines in identifying noun-noun MWEs.