Multi-Word Expression identification using sentence surface features

Much NLP research on Multi-Word Expressions (MWEs) focuses on the discovery of new expressions, as opposed to the identification in texts of known expressions. However, MWE identification is not trivial because many expressions allow variation in form and differ in the range of variations they allow. We show that simple rule-based baselines do not perform identification satisfactorily, and present a supervised learning method for identification that uses sentence surface features based on expressions' canonical form. To evaluate the method, we have annotated 3350 sentences from the British National Corpus, containing potential uses of 24 verbal MWEs. The method achieves an F-score of 94.86%, compared with 80.70% for the leading rule-based baseline. Our method is easily applicable to any expression type. Experiments in previous research have been limited to the compositional/non-compositional distinction, while we also test on sentences in which the words comprising the MWE appear but not as an expression.