Classifying Amharic News Text Using Self-Organizing Maps

Eyassu, Samuel and Gambäck, Björn (2005) Classifying Amharic News Text Using Self-Organizing Maps. In: ACL 2005: 43rd Annual Meeting of the Association for Computational Linguistics; Workshop on Computational Approaches to Semitic Languages, 29 Jun 2005, University of Michigan, Ann Arbor, Michigan, USA.


Official URL:


The paper addresses using artificial neural networks for classification of Amharic news items. Amharic is the language for countrywide communication in Ethiopia and has its own writing system containing extensive systematic redundancy. It is quite dialectally diversified and probably representative of the languages of a continent that so far has received little attention within the language processing field. The experiments investigated document clustering around user queries using Self-Organizing Maps, an unsupervised learning neural network strategy. The best ANN model showed a precision of 60.0% when trying to cluster unseen data, and a 69.5% precision when trying to classify it.

Item Type:Conference or Workshop Item (Paper)
Uncontrolled Keywords:Text classification, Document Clustering, Amharic, Artificial Neural Networks, Self-Organizing Maps
ID Code:173
Deposited By:Userware Researcher
Deposited On:17 Jan 2006
Last Modified:18 Nov 2009 15:54

Repository Staff Only: item control page