An NLP based application which takes Bengali text as input and detects the grammatical errors, analyzes the input based on grammatical rules and marks the errors in output. The application does the stemming, tokenizing, parsing (using ANTLR), and error marking sequentially to produce the output.

Technologies used

  • Python (Backend)
  • JavaFX (Front-end)
  • Natural Language Processing
  • Context Free Grammar (CFG)
  • POS Tagger
  • Stemmer
  • Tokenizer
  • ANTLR (ANother Tool for Language Recognition)

NB. This project was done under the supervision of the Department of Electrical and Computer Engineering at North South University, Dhaka, Bangladesh. The developers, researchers hold the rights of the closed source application.