Esha Banerjee

Esha Banerjee

Ph.D. scholar
Centre for Linguistics, School of Languages, Literature and Culture Studies, Jawaharlal Nehru University, New Delhi - 110067

Research Interests

Natural Language Processing (NLP), Shallow Parsing and Speech processing
Language of interest: Hindi.

Other interests

Indian Language Technology (English, Hindi), Syntactic-Semantic Annotation, Information Retrieval, Machine Translation, Localization

Research & Work Experiences

1. Oct 2010 - Dec 2014: Senior Linguist on the Indian Languages Corpora Initiative (ILCI) project undertaken by a collaboration of leading universities in India (D.I.T. funded, Govt. of India). Job duties included team/project management, data curation, POS tagging, annotation and evaluation of data.
2. Oct 2009 - Oct2010: Junior Linguist on the Indian Languages Corpora Initiative (ILCI) project. Job duties included linguistic translation of Hindi data into English. (Contract Basis).
3. August 2008- June 2009: Freelance consultant with various industry leaders (Appen, Microsoft) for annotation services.
4. January 2008 - April 2008: Worked on building Multilingual-Dictionary Tool as part of a Machine Translation assignment in the Computational Linguistics course during masters. Work included annotation and glossing of Hindi text.

Workshops attended

1. The 9th edition of the Language Resources and Evaluation Conference, held at Reykjavik, Iceland, 26-31 May, 2014.
2. POS workshop for ILCI corpora held at Gujarat University, Ahmedabad, 28-30 September, 2010.
3. The 4th International Sanskrit Computational Linguistics Symposium (4i-SCLS) held at Jawaharlal Nehru University, New Delhi, 10-12 December, 2010.


1. Ph. D. Thesis Title: Prosody Labelling in Hindi TTS. Ongoing.
2. M.Phil. Dissertation Title: Intra phrasal agreement within the Hindi noun phrase: A Grammar Checker Approach JNU, New Delhi, in Linguistics (Computational Linguistics)
4. M.A. English and Foreign Languages University (formerly CIEFL), Hyderabad, in Linguistics
5. B.A. St. Xavier's College (University of Calcutta), in English (Hons.)

National Eligibility Test for Lectureship (NET - June 2013) of the UGC


Computer Skills / Software Familiarity:

OS: Microsoft Windows (XP to 7), Linux (version SUSE 10.1)
Software Packages: Comfortable working with Microsoft Office 2003, 2007 (Word, Excel, Powerpoint, Access). Have working knowledge of Praat, Toolbox, Audacity sound editing software, EditPlus text editor (version 3.10)
Programming Language: Basic knowledge of Python, Java


Hindi (Native), Bengali, English