Malayalam Analyzer and Tamil Generator for Machine Translation

The local language computing has significant implications on the culture of the respective locality. Enabling computers to understand human language is a major challenge in the field of technology. This monograph is an outcome from the research work in the field of Language Computing. Malayalam is spoken in Kerala whereas Tamil in Tamilnadu, both belong to the Dravidian Family, two most prominent regional languages of Indian subcontinent. The first part of the monograph deals with the Morphological Analyzer. Morphological Analyzer segments the word into morphemes and analyze the word formation. The second part of this monograph deals with the importance of bilingual dictionary. The last part deals with the Morphological Generator. The Morphological generator is the reverse process of the Analyzer. The complexity of these languages and less number of work done on this area necessitates the need of this work .The present study gives only word generation and can be extended to sentence level. Further research on this can be done by using machine learning techniques, and of course, this study will be useful for future researchers in this area.

Autorentext

Jisha P. Jayan,MCA from M.G. University,Kerala. Computer Scientist at Virtual Resource Centre for Language Computing (VRCLC), Indian Institute of Information Technology and Management-Kerala (IIITM-K),Technopark - Trivandrum.