Paper: A Connectionist Approach to Prepositional Phrase Attachment for Real World Tuts

ACL ID P98-2201
Title A Connectionist Approach to Prepositional Phrase Attachment for Real World Tuts
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 1998
Authors

Ill this paper we describe a neural network-based approach to prepositional phrase attachment disam- biguation for real world texts. Although the use of semantic classes in this task seems intuitively to be adequate, methods employed to date have not used them very effectively. Causes of their poor results are discussed. Our model, which uses only classes, scores appreciably better than the other class-based methods which have been tested on the Wall Street Journal corpus. To date, the best result obtained using only classes was a score of 79.1%; we obtained an accuracy score of 86.8%. This score is among the best reported in the literature using this corpus.