Prepositional Phrase Attachment Through a Backed-off Model

This paper shows that the problem of prepositional phrase attachment ambiguity is analogous to n-gram language models in speech recognition, and that one of the most common methods for language modeling, the backed-off estimate, is applicable.

Abstract

Recent work has considered corpus-based or statistical approaches to the problem of prepositional phrase attachment ambiguity. Typically, ambiguous verb phrases of the form v rip1 p rip2 are resolved through a model which considers values of the four head words (v, nl, p and n2). This paper shows that the problem is analogous to n-gram language models in speech recognition, and that one of the most common methods for language modeling, the backed-off estimate, is applicable. Results on Wall Street Journal data of 84.5% accuracy are obtained using this method. A surprising result is the importance of low-count events - ignoring events which occur less than 5 times in training data reduces performance to 81.6%.