Combining Neural Networks and Statistics for Chinese Word Sense Discrimination
- Resource Type
- Conference
- Authors
- Fan, DongMei; Lu, Zhimao; Zhang, Rubo
- Source
- 2008 Fourth International Conference on Natural Computation Natural Computation, 2008. ICNC '08. Fourth International Conference on. 3:136-140 Oct, 2008
- Subject
- Computing and Processing
Neural networks
Statistics
Artificial neural networks
Context modeling
Supervised learning
Natural languages
Computer networks
Electronic mail
Mutual information
Statistical analysis
Word Sense Disambiguation
natural language processing
Neural Networks
- Language
- ISSN
- 2157-9555
2157-9563
The input of network is the key problem for Chinese Word sense Discrimination utilizing the Neural Network. This paper presents an input model of Neural Network that calculates the Mutual Information between contextual words and ambiguous word by using statistical method and taking the contextual words to certain number beside the ambiguous word according to (-M, +N). The experiment adopts triple-layer BP Neural Network model and proves how the size of training set and the value of M and N affect the performance of Neural Network model. The experimental objects are six pseudowords owning three word-senses constructed according to certain principles. Tested accuracy of our approach on a closed-corpus reaches 90.31%, and 89.62% on a open-corpus. The experiment proves that the Neural Network model has good performance on Word sense Discrimination.