Novel semantic features for verb sense disambiguation
HLT-Short '08 Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics on Human Language Technologies: Short Papers
To annotate more accurately or to annotate more
LAW IV '10 Proceedings of the Fourth Linguistic Annotation Workshop
Hi-index | 0.00 |
In this paper we describe the results of training high performance Word Sense Disambiguation (WSD) systems on a new data set based on groupings of WordNet senses. This data set is designed to provide clear sense distinctions with sufficient examples in order to provide high quality training data. The sense distinctions are based on explicit syntactic and semantic criteria. Our WSD features utilize similar syntactic and semantic linguistic information. We demonstrate that this approach, using both Maximum Entropy and SVM models, produces systems whose performance is comparable to that of humans.