Attaching Multiple Prepositional Phrases: Generalized Backed-oo Estimation

There has recently been considerable interest in the use of lexically-based statistical techniques to resolve preposition-al phrase attachments. To our knowledge , however, these investigations have only considered the problem of attaching the rst PP, i.e., in a V NP PP] conngura-tion. In this paper, we consider one technique which has been successfully applied to this problem, backed-oo estimation, and demonstrate how it can be extended to deal with the problem of multiple PP attachment. The multiple PP attachment introduces two related problems: sparser data (since multiple PPs are naturally rarer), and greater syntactic ambiguity (more attachment conngurations which must be distinguished). We present and algorithm which solves this problem through re-use of the relatively rich data obtained from rst PP training, in resolving subsequent PP attachments .