AUTOMATIC SENTENCE PARSER FOR AMHARIC LANGUAGE USING SVM

Natural language processing is a research area which is becoming increasingly popular each day for both academic and commercial reasons. Higher level NLP systems (e.g., machine translation) are materialized only when the lower ones (e.g., part-of-speech tagger, syntactic parser) are successfully built.

The objective of this research is to build and evaluate Automatic Amharic sentence parser using supervised machine learning approach specifically by using support vector machine. In order to conduct the experiment, we adopt LIBSVM package, which is a library for Support Vector Machines (SVMs).

To do this research, 370 sample sentences were taken from WIC corpus, Amharic grammar book, news article, magazines; manually parsed the entire sentence by the researcher and comment and suggestion given from linguistics expert. These datasets are classified into 90% is for training and the rest 10 % is used for testing.

Experiments have been conducted in this study using the training set and test set. Finally, the overall model accuracy of the mode that we have got is 98.913.

Keywords: Parser, Amharic Text Parser using SVM, Text Parser, Parser.