Hi, thanks for your interest. We know, we always suffer from scarcity of good tools/resources for processing Bengali text. BNLP is a great initiative to solve this problem. Your contribution can make this initiative more powerful and also help millions of Bengali developer to process Bengali language more efficiently.
- Bengali Tokenization
- Bengali Word Embedding
- Bengali Document Emebdding
- Bengali POS Tagging
- Bengali NER
- Bengali Text Cleaning
- Bengali Corpus
To make this tool more effective you can add below features as well as other features too
- Bengali Lemmatization
- Bengali Spell Checker
- so on..................
In this document, we summarize everything, so that you can contribute easily and make this tool more powerful.
We hosted our code repositories in Github for better management of issues and development.
- bnlp is the main repository with code related library
- Fork the bnlp repository on GitHub to your account;
- Clone your forked repository locally
(
git clone https://github.com/<your-github-username>/bnlp.git
); - Run
cd bnlp
to get to the root directory of thebnlp
code base; - Download the pretrianed models for running tests (you can find the pretrained model details here in Readme
- To add new feature inside bnlp/bnlp create your objective script with proper testing.
- To modify any script please do modification with proper testing and send pull request.
- Use issue tab for issue, bug reporting or discussion.
Thanks and Happy coding!