Prepositional Phrase Attachment through a Backed-Off Model

Prepositional Phrase Attachment through a Backed-Off Model (1995)

by Michael Collins , James Brooks

Venue:	In Proceedings of the Third Workshop on Very Large Corpora
Citations:	122 - 5 self

Datum	Value	Source
TITLE	Prepositional Phrase Attachment through a Backed-Off Model	SVM HeaderParse 0.1
AUTHOR NAME	Michael Collins	SVM HeaderParse 0.1
AUTHOR ADDR	Philadelphia, PA 19104	SVM HeaderParse 0.1
AUTHOR NAME	James Brooks	SVM HeaderParse 0.1
AUTHOR ADDR	Philadelphia, PA 19104	SVM HeaderParse 0.1
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 np1 p np2 are resolved through a model which considers values of the four head words (v, n1, 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%. 1	SVM HeaderParse 0.1
CITATIONS	7 found	ParsCit 1.0