Word sense disambiguation and information retrieval
SIGIR '94 Proceedings of the 17th annual international ACM SIGIR conference on Research and development in information retrieval
Context-sensitive learning methods for text categorization
ACM Transactions on Information Systems (TOIS)
Feature Engineering for Text Classification
ICML '99 Proceedings of the Sixteenth International Conference on Machine Learning
Using a semantic concordance for sense identification
HLT '94 Proceedings of the workshop on Human Language Technology
Hi-index | 0.00 |
Many popular Text Classification (TC) models use simple occurrence of words in a document as features to base their classifications. They commonly assume word occurrences to be statistically independent in their design. Although such assumption does not hold in general, these TC models are robust and efficient in their task. Some recent studies have shown context-sensitive TC approaches were able to perform better in general. On the other hand, although complex linguistic or semantic features may intuitively be more relevant in TC, studies on their effectiveness have produced mixed and inconclusive results. In this paper, we present our investigation on the use of some complex linguistic features with two context-sensitive TC methods. Our experimental results show potential advantages of such approach.