Combining Methods for Word Sense Disambiguation of WordNet Glosses.
Adrian Novischi · 2004
This paper presents a new approach for combining differ-ent semantic disambiguation methods that are part of a Word Sense Disambiguation(WSD) system. The way these meth-ods are combined greatly influences the overall system per-formance. The approach is based on generating training ex-amples, for each sense of the word, based on the output of each disambiguation method. A set of rules is learned from the training examples and then applied to optimize the output of the WSD system. We tested this approach on disambiguat-ing WordNet glosses. However the approach is applicable to any WSD system. Our approach yielded a 3 % gain in per-formance when compared with more traditional approaches such as selecting the sense given by the best disambiguation method or summing up the contribution of each method.