A Supervised Model for Extraction of Multiword Expressions Based on Statistical Context Features

摘要

We present a method for extracting Multiword Expressions (MWEs) based on the immediate context they occur in, using a supervised model. We show some of these contextual features can be very discriminant and combining them with MWE-specific features results in a relatively accurate extraction. We define context as a sequential structure and not a bag of words, consequently, it becomes much more informative about MWEs.