Natural Language Processing (NLP) research include understanding and developing the core linguistic modules such as tokenizer, lemmatizer, pos tagger, syntactic parser. The development of these modules also includes developing linguistic resources such as annotated corpus for each specific modules.
These are important for developing Information Extraction, which again comprised of developing independent modules such as Named Entity Recognition, Relation Extraction, Anaphora Resolution, Event Detection and so on. As a part of these works, we are working on the development of Bangla Content Annotation Bank.
