[Student-projects] GSOC'14: Spell checker

[Jaseem Umar]

For the spellchecker, Lttoolbox is handling compounds and inflections,
pretty decently. Wouldn't that be better than Hunspell?
Eg:- http://wiki.smc.org.in/User:Jaseem/spellcheck#Lttoolbox


On Sat, Mar 8, 2014 at 5:47 PM, Santhosh Thottingal <
santhosh.thottingal at gmail.com> wrote:

> Hi Shafeeq,
>
>
> http://wiki.smc.org.in/SoC/2014/Project_ideas#A_spell_checker_for_Indic_language_that_understands_inflectionshas a link to all my conversation with the author of Hunspell in the past.
> Please check it out.
>
> Please check this mail too
>
> http://lists.smc.org.in/pipermail/student-projects-smc.org.in/2014-March/000056.html
>
> On Thursday, March 6, 2014, Shafeeq K <shafeeq94 at gmail.com> wrote:
>
>> Hi,
>> I'm Shafeeq, a second year CSE student from NSS College of
>> Engineering, Palakkad.
>> I am interested in this year's GSOC project "A spell checker for Indic
>> language that understands inflections". I've been reading and doing a
>> little of homework for this project, as suggested by the mentor.
>>
>> I couldn't find any affix rules for malayalam in the corresponding
>> affix file. Does that mean currently we rely only on the collection of
>> words for spell check?
>>
>
> Yes, that is right. Two links about a related discussion.
>
>    - ചരിത്രത്തെ വീണ്ടെടുക്കുക <http://www.chintha.com/node/3003>:
>    തര്‍ജ്ജനി മാസികയില്‍ സോമനാഥന്‍ . പി എഴുതിയ ലേഖനം
>    - വേണം നമുക്ക് ഏകീകൃതമായ ഒരെഴുത്തുരീതി <http://chintha.com/node/2967>:
>    തര്‍ജ്ജനി മാസികയില്‍ സോമനാഥന്‍ . പി എഴുതിയ ലേഖനം
>
>
>
>
>>
>> Hunspell manual suggests only two-fold suffix stripping. Since it was
>> mentioned that Indic languages might require as much as 5 levels of
>> stripping, is Hunspell the way forward? I saw an experimental
>> indic-stemmer in SILPA. Couldn't we expand it to handle the multilevel
>> suffix stripping?
>>
>
>
> Please check
> http://wiki.smc.org.in/User:%E0%B4%B8%E0%B4%A8%E0%B5%8D%E0%B4%A4%E0%B5%8B%E0%B4%B7%E0%B5%8D/HunspellConversation
>
>
>
>
>> About the agglutinations of words and suffixes, I came across a paper
>> while reading about it [1]. Could you please suggest some other
>> documents as well?
>>
>> Thanks.
>>
>> [1]: http://aclweb.org/anthology//O/O12/O12-1028.pdf
>>
>>
>> Shafeeq
>> _______________________________________________
>> Student-projects mailing list
>> Student-projects at lists.smc.org.in
>> http://lists.smc.org.in/listinfo.cgi/student-projects-smc.org.in
>>
>
> _______________________________________________
> Student-projects mailing list
> Student-projects at lists.smc.org.in
> http://lists.smc.org.in/listinfo.cgi/student-projects-smc.org.in
>
>


-- 
Jaseem
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.smc.org.in/pipermail/student-projects-smc.org.in/attachments/20140312/53d92941/attachment.html>