Structural ambiguity and lexical relations
Computational Linguistics - Special issue on using large corpora: I
Building a large annotated corpus of English: the penn treebank
Computational Linguistics - Special issue on using large corpora: II
A rule-based approach to prepositional phrase attachment disambiguation
COLING '94 Proceedings of the 15th conference on Computational linguistics - Volume 2
A maximum entropy model for prepositional phrase attachment
HLT '94 Proceedings of the workshop on Human Language Technology
The benefit of stochastic PP attachment to a rule-based parser
COLING-ACL '06 Proceedings of the COLING/ACL on Main conference poster sessions
Decision trees for sense disambiguation of prepositions: case of over
CLS '04 Proceedings of the HLT-NAACL Workshop on Computational Lexical Semantics
Prepositions in applications: A survey and introduction to the special issue
Computational Linguistics
Handling of prepositions in English to Bengali machine translation
Prepositions '06 Proceedings of the Third ACL-SIGSEM Workshop on Prepositions
Simple preposition correspondence: a problem in English to Indian language machine translation
SigSem '07 Proceedings of the Fourth ACL-SIGSEM Workshop on Prepositions
Preposition senses: generalized disambiguation model
CICLing'06 Proceedings of the 7th international conference on Computational Linguistics and Intelligent Text Processing
| Hi-index | 0.00 |
In 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.