Complex, Corpus-Driven, Syntactic Features for Word Sense Disambiguation

Although syntactic features offer more specific information about the context surrounding a target word in a Word Sense Disambiguation (WSD) task, in general, they have not distinguished themselves much above positional features such as bag-of-words. In this paper we offer two methods for increasing the recall rate when using syntactic features on the WSD task by: 1) using an algorithm for discovering in the corpus every possible syntactic feature involving a target word, and 2) using wildcards in place of the lemmas in the templates of the syntactic features. In the best experimental results on the SENSEVAL-2 data we achieved an Fmeasure of 53.1% which is well above the mean F-measure performance of official SENSEVAL-2 entries, of 44.2%. These results are encouraging considering that only one kind of feature is used and only a simple Support Vector Machine (SVM) running with the defaults is used for the machine learning.