A MWE lexicon formalism optimised for observational adequacy

Abstract

Past research advocates that, in order to handle the unpredictable nature of multiword expressions (MWEs), their identification should be assisted with lexicons. The choice of the format for such lexicons, however, is far from obvious. We propose the first -to our knowledge -method to quantitatively evaluate some MWE lexicon formalisms based on the notion of observational adequacy. We apply it to derive a simple yet adequate MWE-lexicon formalism, dubbed λ-CSS, based on syntactic dependencies. It proves competitive with lexicons based on sequential representation of MWEs, and even comparable to a state-of-the art MWE identifier.