Machine learning in automated text categorization
ACM Computing Surveys (CSUR)
On arabic search: improving the retrieval effectiveness via a light stemming approach
Proceedings of the eleventh international conference on Information and knowledge management
Rational Kernels: Theory and Algorithms
The Journal of Machine Learning Research
Learning languages with rational kernels
COLT'07 Proceedings of the 20th annual conference on Learning theory
OpenFst: a general and efficient weighted finite-state transducer library
CIAA'07 Proceedings of the 12th international conference on Implementation and application of automata
LIBSVM: A library for support vector machines
ACM Transactions on Intelligent Systems and Technology (TIST)
| Hi-index | 0.00 |
Many stemming techniques are used in the context of Arabic Text Classification. In this paper, we show the effect of stemming on classification systems. We introduce a new stemming technique -approximate stemming- based on the use of Arabic patterns. These patterns are modeled using transducers and stemming is done without depending on any dictionary. Using transducers for stemming words, documents are transformed into finite state transducers. This allow us to use rational kernels as a framework for Arabic Text Classification. Experiments show that, when compared with other approaches, our approach is more effective specially in term of Accuracy, Recall and F1.