Dear Himanshu:
I am copying the message to the project list (apertium-stuff), just in
case someone else wants to follow up.
You mention 5 African language pairs. Which language pair are you
proficient in?
If you think you are well equipped to tackle the building of a
rule-based (not neural) MT system based on the Apertium platform for
these languages, you could submit your proposal to our organization.
See: http://wiki.apertium.org/wiki/Top_tips_for_GSOC_applications .
Best regards,
Mikel
El 3/3/20 a les 21:15, Himanshu choudhary ha escrit:
Dear professor Forcada,
My name is Himanshu and I am a student of Delhi College of
Engineering India. I am highly interested to work on the projects
"Create a usable version of one of these language pairs:
English--Igbo, English--Yoruba, English--Tigrinya, English--Swahili,
English-Hausa".
I have also worked and previously published some research papers on
Machine Translation. I have searched the data for these languages on
the Internet and found some.
I just want to ask can't we use Neural machine translation or
unsupervised machine translation rather than rule-based learning.
Please let me know so that I can work on it.
Thank You
--
Mikel L. Forcada http://www.dlsi.ua.es/~mlf/
Departament de Llenguatges i Sistemes Informàtics
Universitat d'Alacant
E-03690 Sant Vicent del Raspeig
Spain
Office: +34 96 590 9776
_______________________________________________
Apertium-stuff mailing list
Apertium-stuff@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/apertium-stuff
