Hi Suraj,
A pair involving Sanskrit is a bad choice for Apertium because of *sandhi*.
For example, the sentence जानामि अहम् (*jaanaami aham*, 'I know') is
actually written as one word: जानाम्यहम् (*jaanaamyaham*, 'I know'). Any
number of words can be joined together like this with *sandhi*, regardless
of part-of-speech, and furthermore those words are inflected too (like the
example). To analyze Sanskrit text, you would have to be able to break
the *sandhi
*of arbitrarily inflected forms; this is not trivial, not easily possible
with Apertium tools (I believe), and definitely very hard to disambiguate
when you have multiple possible breaks in a word.
Maybe you can work on another language pair involving Indian languages, if
you know anything beyond Sanskrit and Hindi?
Shardul
On Sat, Mar 24, 2018 at 3:00 PM, Suraj Tamgale <sbtamg...@gmail.com> wrote:
> hi everyone,
> i've submitted the proposal.i will be extremely happy if someone take a
> look at it and give review.
>
> link to my draft: hhttps://docs.google.com/document/d/11uI3WsQ5_
> L4HEyETqqgmzXTsR7fUSCd01fKe8VhekXM/edit?usp=sharing
>
>
> ------------------------------------------------------------
> ------------------
> Check out the vibrant tech community on one of the world's most
> engaging tech sites, Slashdot.org! http://sdm.link/slashdot
> _______________________________________________
> Apertium-stuff mailing list
> Apertium-stuff@lists.sourceforge.net
> https://lists.sourceforge.net/lists/listinfo/apertium-stuff
>
>
------------------------------------------------------------------------------
Check out the vibrant tech community on one of the world's most
engaging tech sites, Slashdot.org! http://sdm.link/slashdot
_______________________________________________
Apertium-stuff mailing list
Apertium-stuff@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/apertium-stuff
