Standardization, Research Areas, Linguistic Resources & Tools, Technology Handshake
Jadavpur University was a language vertical member in the ILMT consortia. We have created 14K Hindi-Bengali synsets, 140 Hindi-Bengali Function-Word synsets, 170 Hindi-Bengali verb synset and these synsets are cross-linked.Tourism corpus (44K) collected and annotated. Gold standard data has been created and evaluated with the help of evaluation software.
Natural Language Processing, Machine Translation, Information Retrieval
Domain of Expertise
Research Areas, Linguistic Resources & Tools, Application Showcase
We at Banasthali University, developed the English to Hindi Parallel Corpus, where we collected 16,000 sentence in tourism domain and 6,000 sentence in Health Domain. We also developed an MT Evaluation Suite which performs subjective human evaluation and automatic evaluation of the engine output based on different automatic evaluation metrics.
I have published & research papers in area of NLP and speech processing in many international conferences.Currently i am working in EILMT-II Project since 2007,feb.I am also a Phd Student of CSE Dept. Jadavpur university.