Word association norms, mutual information, and lexicography
Computational Linguistics
Introduction to the theory of neural computation
Introduction to the theory of neural computation
Natural language understanding (2nd ed.)
Natural language understanding (2nd ed.)
Human-computer interaction
Statistical Language Learning
A simple rule-based part of speech tagger
ANLC '92 Proceedings of the third conference on Applied natural language processing
A methodology for automatic term recognition
COLING '94 Proceedings of the 15th conference on Computational linguistics - Volume 2
Surface grammatical analysis for the extraction of terminological noun phrases
COLING '92 Proceedings of the 14th conference on Computational linguistics - Volume 3
Extracting nested collocations
COLING '96 Proceedings of the 16th conference on Computational linguistics - Volume 1
Hi-index | 0.00 |
In recent years, there has been a conscious move away from rule based methods of term acquisition with research focusing on alternative machine learning approaches. This comes as a response to the difficulties of complete knowledge representation of term formation as a general set of rules. This paper is a continuation of our initial research into connectionist approaches to term recognition [13]. An extension to the Winner-take-all algorithm is proposed which uses exhaustive testing of weights to elucidate term and non-term forming clusters. This algorithm is applied to automatic term recognition. Initial experiments have shown improved results ranging between 1.31% and 5.86% after initial training.