I am working on natural language processing specially on Tamil language. I need a tool to tag my tamil corpus. can any one tell me a good POS tool freely available to download. I also need how many patterns (example Subject+verb+object etc..) are there in Tamil grammar to form a sentence.
If anyone working on this field please help me.
similarly I need large amount of Tamil corpus for my research.
Is there any Tamil corpus freely available to download?
You can have a look here :
http://nlp.amrita.edu:8080/NLP4U/download.html
For POS tagging and chunking you may look at: http://ltrc.iiit.ac.in/showfile.php?filename=downloads/shallow_parser.php
As for the corpus, what about using wikipedia? http://dumps.wikimedia.org/tawiki
Cheers!
Though I do not know of Tamil corpus, I think a way forward might be to start on a small scale, building in bits. You might train your own Tagger over time. Though in English, I believe this link might help.
http://www.codeproject.com/Articles/12109/Statistical-parsing-of-English-sentences
CLRG, AU-KBC Research Centre has released Tamil POS corpus and POS tagger.
More information is available in the following link,
http://au-kbc.org/nlp/corpusrelease.html
Technology Development for Indian Language (TDIL), has several useful NLP tools and corpora freely available.
https://tdil-dc.in/index.php?option=com_download&task=showresourceDetails&toolid=356&lang=en