Amharic Part-of-Speech Tagger for Factored Language Modeling
Martha Yifiru Tachbelie, Wolfgang Menzel · 2009
This paper presents Amharic part of speech taggers developed for factored language modeling. Hidden Markov Model (HMM) and Support Vector Machine (SVM) based taggers have been trained using the TnT and SVMTool. The overall accuracy of the best performing TnT- and SVM-based taggers is 82.99% and 85.50%, respectively. Generally, with respect to accuracy SVM-based taggers perform better than TnTbased taggers although TnT-based taggers are more ecient with regard to speed and memory requirement. We have developed factored language models (with two and four parents) for which the estimation of the probability for each word depends on the previous one or two words and their POS. These language models have been used in an Amharic speech recognition task in a lattice rescoring framework and a significant improvement in word recognition accuracy has been observed.