TITLE: Prepositional Phrase Attachment Ambiguity Resolution using Semantic Hierarchies
SPEAKER: Kailash Nadh (Middlesex University)

ABSTRACT:

This paper describes a system that resolves prepositional phrase attachment ambiguity in English sentence processing.  This attachment problem is ubiquitous in English text, and is widely known as a place where semantics determines syntactic form.  The decision is made based on a four-tuple composed of the head verb of the verb phrase, the head noun of the noun phrase, and the preposition and head noun in the prepositional phrase.  A corpus with known results, the Penn Treebank, is used for training and testing purposes.  During training, known results are used to build a lattice of hierarchical categories taken from WordNet.  These lattices are then compared to the novel lattices derived from the test four-tuples. The results of the system are 90.53% correct attachment decisions.