A Detection Algorithm for Multiword Verbs in the English Sub-language of MEDLINE Abstracts
In: Proceedings Coling 2004. ??.
In this paper, we investigate the multiword verbs in the English sub-language of MEDLINE abstracts. Based on the integration of the domain-specific named entity knowledge and syntactic as well as statistical information, this work mainly focuses on how to evaluate a proper multiword verb candidate. Our results present a sound balance between the low- and high-frequency multiword verb candidates in the sub-language corpus. We get a F-measure of 0.753, when tested on a manual sample subset consisting of multiword candidates with both low- and high-frequencies.