[Student-projects] GSoC 2014 A spell checker for Indic language that understands inflections

[Priya Pappachan]

Hi,

  I'm Priya Pappachan.I m doing my B tech Computer Science in Govt.
Engineering College,Thrissur.

  I'm interested in the project 'A Spell checker for Indic language that
understands inflections'. I'd like to develop spellchecker for malayalam.
 I read about how hunspell is written for languages and about files of
hunspell. I had a look at how it is done in tamil from the link given in
wiki page and tried hunspell in malayalam. Also I have a knowledge about
how hunspell files are written for prefix,suffix,compounding etc in
language. Hunspell can also be used for two fold suffix stripping.

  The main task will be writing affix file in hunspell for malayalam. A
classification of words in malayalam is necessary for writing the affix
file for the spell checker.

   I started studying rules that is to be followed for the language while
writing affix file. The different sandhi rules and it's issues in the
language has to be known. I also understood about the challenges that can
occur while scripting due to complexity in rules of malayalam grammar
system. The plan is to use hunspell algorithm. If it doesn't work in
hunspell, an algorithm to be implemented in python has to be found out.

IRC handle  : pratyas on irc.freenode.net

How should I work towards the project? Please provide me some guidelines.

-- 
Priya
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.smc.org.in/pipermail/student-projects-smc.org.in/attachments/20140304/afb5b5f2/attachment-0002.htm>