To date, parsers have made limited use of semantic information, but there is evidence to suggest that semantic features can enhance parse disambiguation. This paper shows that semantic classes help to obtain significant improvement in both parsing and PP attachment tasks. We devise a gold-standard sense- and parse tree-annotated dataset based on the intersection of the Penn Treebank and SemCor, and experiment with different approaches to both semantic representation and disambiguation. For the Bikel parser, we achieved a maximal error reduction rate over the baseline parser of and , for parsing and PP-attachment respectively, using an unsupervised WSD.
