foysal87 / sbnltk

Bangla NLP toolkit. Bangla NER, POStag, Stemmer, Word embedding, sentence embedding, summarization, preprocessor, sentiment analysis, etc.

HELLO!

I'm Towhid Ahmed Foysal, a Competitive programmer and NLP researcher.I am a Software Engineer at Orbitax, which is one of the biggest International tax software Industries in the world. I have a great passion in Problem Solving and Natural Language Processing Research.

✇ Competitive Programmming:

ONLINE JUDGE

✇ Research Area:

RESEARCH

✇ Skills:

Preferred Languages

Integrated Development Environment(IDE)

Database

Tools Used

✇ Current Status:

- 🌱 I’m currently working on Natural Language Processing Toolkit (sbnltk) and in orbitax Bangladesh Limited
- 🤝 I’m looking for help in Bangla Corpus Collection
- 📫 I'm learning c#,dotnet,angular,...
- 👯 I’m looking to collaborate on Bangla NLP toolkit(sbnltk)
- 🕸️ Ask me about Problem Solving and Deep learning
- 🌀 Trying to blog at github
- 💬 You can reach me [email protected]
- ⚡ Gaming: COD, PUBG ,Valorant and Fall Guys

✇ My Github Stats:

✇ Publications:

1. Bangla Extractive Text Summarization

sbnltk's Issues

pretained models not found

I wanted to run the sentiment analysis on my own dataset. But, while running sbnltk, the downloader could not download any of the models because they are kept in all private drives. Can anyone update those models to being public

Details about sentence embedding model trained on human translated data called "sentence_embedding_transformer_hd""

@Foysal87 May I know exactly which transformer model have you used? Is it a custom model or a traditional model like bert. Is the model available on HuggingFace Models Hub? Also is the human translated data publicly available?

details about sentence transformer

your readme.md says your training data is 3,00,000+ human data and 3,00,000+ google translated data. I want to know if it's 300,000+ documents or 300,000+ sentences. It would also be helpful to provide the link to the dataset you used to train the sentence transformers.