Prepositional Phrase Attachment through a Backed-Off Model

dc.creatorCollins, Michael
dc.creatorBrooks, James
dc.date1995-06-22
dc.date.accessioned2026-07-07T09:09:56Z
dc.date.available2026-07-07T09:09:56Z
dc.descriptionRecent 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%.
dc.descriptionTo appear in Proceedings of the Third Workshop on Very Large Corpora, 12 pages, LaTeX
dc.identifierhttps://arxiv.org/abs/cmp-lg/9506021
dc.identifierhttp://arxiv.org/abs/cmp-lg/9506021
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/151212
dc.subjectComputation and Language
dc.titlePrepositional Phrase Attachment through a Backed-Off Model
dc.typetext

Files

Collections