Skip Navigation

Literary and Linguistic Computing 1996 11(4):187-192; doi:10.1093/llc/11.4.187
© 1996 by Association for Literary & Linguistic Computing
This Article
Right arrow Alert me when this article is cited
Right arrow Alert me if a correction is posted
Services
Right arrow Email this article to a friend
Right arrow Similar articles in this journal
Right arrow Alert me to new issues of the journal
Right arrow Add to My Personal Archive
Right arrow Download to citation manager
Right arrowRequest Permissions
Google Scholar
Right arrow Articles by Wu, H
Right arrow Articles by Furugori, T
Right arrow Search for Related Content
Social Bookmarking
Add to CiteULike   Add to Connotea   Add to Del.icio.us  
What's this?

A hybrid disambiguation model for prepositional phrase attachment

H Wu and T FurugoriZ

Department of Computer Science, The University of Electro-Communication, Chofu, Tokyo, Japan Z Corresponding author

Prepositional Phrase (PP) attachment is a major cause of structural ambiguity in natural language. Many proposals have increasingly relied on large-scale corpus to resolve this problem. However, this approach encounters the notorious sparse-data problem that produces poor results on disambiguation. We in this paper offer a hybrid method which integrates corpus-based approach with knowledge-based techniques for PP attachment disambiguation. It explores a wide-variety of information, including co-occurrence frequencies from annotated corpora, conceptual relationships and conceptual features for a machine-readable dictionary, and syntactic clues from our linguistic observations. We use dictionary definitions and human knowledge to overcome the sparse-data problem. An experiment shows an accuracy rate of 87.7% of our method over 3043 sentences in real English text that contain ambiguous PPs. This result is better than those of any existing methods.


Add to CiteULike CiteULike   Add to Connotea Connotea   Add to Del.icio.us Del.icio.us    What's this?




Disclaimer: Please note that abstracts for content published before 1996 were created through digital scanning and may therefore not exactly replicate the text of the original print issues. All efforts have been made to ensure accuracy, but the Publisher will not be held responsible for any remaining inaccuracies. If you require any further clarification, please contact our Customer Services Department.