Unsupervised word sense disambiguation rivaling supervised methods
ACL '95 Proceedings of the 33rd annual meeting on Association for Computational Linguistics
Using an ontology to determine English countability
COLING '02 Proceedings of the 19th international conference on Computational linguistics - Volume 1
Learning the countability of English nouns from corpus data
ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1
Web-based models for natural language processing
ACM Transactions on Speech and Language Processing (TSLP)
HLT '91 Proceedings of the workshop on Speech and Natural Language
A plethora of methods for learning English countability
EMNLP '03 Proceedings of the 2003 conference on Empirical methods in natural language processing
Detecting article errors based on the mass count distinction
IJCNLP'05 Proceedings of the Second international joint conference on Natural Language Processing
Hi-index | 0.00 |
Countability of English nouns is important in various natural language processing tasks. It especially plays an important role in machine translation since it determines the range of possible determiners. This paper proposes a method for reinforcing countability prediction by introducing a novel concept called one countability per discourse. It claims that when a noun appears more than once in a discourse, they will all share the same countability in the discourse. The basic idea of the proposed method is that mispredictions can be correctly overridden using efficiently the one countability per discourse property. Experiments show that the proposed method successfully reinforces countability prediction and outperforms other methods used for comparison.