Introduction:
The dissertation is an R&D effort at the M. Phil. level for developing a Subanta Recognition and Analysis System (SRAS) based on the subanta formulations of PŒöini. The work consists of the following –
1. comprehensive research on the subanta rules of A·ŒdhyŒy´ (AD), SiddhŒnta Kaumud´ (SK), and KŒ§ikŒ V¨tti (KV),
2. formalizing the subanta rules of PΚini and developing the rule base,
3.creating linguistic resources appropriate for subanta recognition and analysis
4. creating an example base of pronouns, exceptions, and other typical subantas
5. creating a database of basic verb forms of about 90,000 verbs (of 500 commonly occurring verb roots)
6. creating an avyaya list of 520 entries
7. creating a test corpus of 120 electronic files of modern Sanskrit usage
8. creating a testing corpus of 500 common verb roots with added lyap primary
suffix ending
9. creating a testing corpus of 500 common verb roots with added ktvΠprimary suffix ending
10. creating a testing corpus of 500 common verb roots with added tumun primary suffix ending
11. creating a corpus of Pa–catantra stories
12. creating another corpus of some stories, essay and other from Sanskrit magazines and other resources
13. studying the feasibility of a Unicode online system for subanta recognition and analysis
14. evaluating the tools and techniques used – JSP for front end, Java for servlet objects, and MS-SQL Server 2005 for backend, JDBC for connectivity and Apache-Tomcat for web server
15. creating two systems – one for running in a server based non-portable environment with RDBMS as back-end, and other for stand-alone like environment but on Tomcat/Apache web server
Summary of chapters:
Chapter I
Discusses morphological analyzers, current status of R&D in this
field, structure and organization of of AshTAdhyAyI (AD), and subanta of
Panini.
Chapter II
Discusses subanta formalism of Panini and mechanisms to
recognize verb, avyaya and subanta in Sanskrit text.
Chapter III
Discusses the analysis of subanta-padas.
Chapter IV
Discusses the implementation aspects: the front end, Java
objects, databases, linguistic resources (corpus and rule bases and example
bases), how they work and what is basic requirement of the system and how
to apply sandhi and subanta rule where ever necessary.
Conclusion
Discusses future R&D, limitations of the system and result analysis.
This research has been developed a Morphological Analyzer for Sanskrit access on http://sanskrit.jnu.ac.in/subanta/rsubanta.jsp
please try it
|
E-mail this message to a friend
