Clustering words by syntactic similarity improves dependency parsing of predicate-argument structures

Abstract

We present an approach for deriving syntactic word clusters from parsed text, grouping words according to their unlexicalized syntactic contexts. We then explore the use of these syntactic clusters in leveraging a large corpus of trees generated by a high-accuracy parser to improve the accuracy of another parser based on a different formalism for representing a different level of sentence structure. In our experiments, we use phrase-structure trees to produce syntactic word clusters that are used by a predicate-argument dependency parser, significantly improving its accuracy.