POS tagging for Other languages (like SinhaliesTamil)

by: TRomesh, 8 years ago

Last edited: 8 years ago

I'm planning to create a app that will categorize all the words in a sentence to Nouns, Verbs etc..
ive went through some examples and documentations but I couldn't find a way to do it with other languages(Non English).  it would me nice if I could get some references / libraries to implement this app. feather I found out that using NLTK and Scikit-learn is the most suited libraries.  


You must be logged in to post. Please login or register an account.



You would need to train your own part of speech tagger. To do that, you need to use some machine learning algorithm against a dataset with at least 100,000 sentences, all with their parts of speech tagged.

-Harrison 8 years ago

You must be logged in to post. Please login or register an account.