Publication Type : Conference Paper
Publisher : Proceedings of the International Conference on Inventive Computation Technologies,
Source : Proceedings of the International Conference on Inventive Computation Technologies, ICICT 2016, Institute of Electrical and Electronics Engineers Inc., Volume 1 (2017)
ISBN : 9781509012855
Keywords : Baseline mt, Bleu scores, Comparative studies, Computer aided language translation, European languages, Factored mt, language processing, Linguistics, Morphological variants, Speech transmission, Statistical machine translation
Campus : Bengaluru, Mysuru
School : Department of Computer Science and Engineering, School of Arts and Sciences, School of Engineering
Department : Computer Science, Mathematics
Year : 2017
Abstract : Dravidian languages are highly agglutinative and morphologically rich in their features. Language processing for these languages requires more annotating data compared to European or Indo-European languages. In this paper we present the comparison between Statistical Machine Translation (SMT) model with linguistic and nonlinguistic data models for English to Kannada languages. The experiments shows an improvement in Bleu-Score for Factored MT system against Baseline MT system for English to Kannada SMT. Kannada fonts can take ten different forms in representing a word any change of a font variant in word leads to change in meaning of the word. We model these morphological variants of Kannada lemma words, their variants and PoS as Factors in our MT System.
Cite this Research Publication : K. Ma Shivakumar, Shivaraju, Na, Sreekanta, Vb, and Dr. Deepa Gupta, “Comparative study of factored SMT with baseline SMT For English to Kannada”, in Proceedings of the International Conference on Inventive Computation Technologies, ICICT 2016, 2017, vol. 1.