User talk:Priyapappachan/GSoC-spellchecker: Difference between revisions
From SMC Wiki
No edit summary |
No edit summary |
||
Line 9: | Line 9: | ||
You may want to try one or two word formation with Hunspell to get a feel of the project | You may want to try one or two word formation with Hunspell to get a feel of the project | ||
--[[User:സന്തോഷ്|സന്തോഷ്]] ([[User talk:സന്തോഷ്|talk]]) 23:46, 27 April 2013 (PDT) | --[[User:സന്തോഷ്|സന്തോഷ്]] ([[User talk:സന്തോഷ്|talk]]) 23:46, 27 April 2013 (PDT) | ||
Revision as of 18:13, 30 April 2013
Hi, Would it be possible to do some more in depth study into the complexities of multi level suffix stripping or any kind of agglutination, inflection properties of Malayalam. The challenge is not only technical but also linguistics. The suffixes that you mentioned, cannot be created for Malayalam as easy. It need systematic classification of possible suffixes based on 7 prathyaya rules. That too cannot be done without some level automation. I would recommend you to do a thorough reading of the following materials
- http://thottingal.in/documents/MalayalamComputingChallenges.pdf
- http://thottingal.in/documents/PSomanathan_On_Malayalam.pdf
- http://thottingal.in/documents/rachana-malayalam-collation.pdf
- http://www.chintha.com/node/2967
- http://lists.smc.org.in/pipermail/discuss-smc.org.in/2013-March/015062.html
You may want to try one or two word formation with Hunspell to get a feel of the project --സന്തോഷ് (talk) 23:46, 27 April 2013 (PDT)