## BIO
RESUME 1. BIODATA OF SUBHABRATA BANERJEE. 2. Subject of work : Investigation of Natural Languages. 3. Summary of Research : Natural Language Processing of Indian languages. 4. Areas of Specialization: Linguistic Theory Word Sense Disambiguation Parsing Statistical Language Modelling. 5. PATENTS. Saraswati Machine Translation System for English to Bengali and Vice Versa. Lexical Analyser of Bengali, Hindi,Telugu. WSD Systems for Bengali, Hindi and English. Author Identifier System for Bengali. Lexical Filler System for Bengali. Automatic Text Retrieval System for Bengali. 6. JOURNAL PAPERS: Serial Numbers Title Abstract Authors Name of the Journal 1 Word Sense Disambiguation and its Application in Ellipsis Resolution. WSD Technology is applied to resolve gapped structure. S.BanerjeeandS.Bhattacharya. Computational Linguistics. 2 HMM Resolution of the Stylistics problems in Bangla. Stylometry is the phenomenon of mathematical analysis of Stylistics. Using HMM technique we tried to devise the author identification model. S.Banerjee Journal of Artificial Intelligence Research. 3 Word Sense Disambiguation and WordNet Technology. WordNet Technology is a work for WSD Technology in our work we tried to revise the work and gave a better formulation than WordNet.The definition of homograph is changed. S.Banerjee and B.P.Mullick. Language and Literary Computing. 4 Gap Resolution in Bangla. The resolution of gap is done in Bangla.The work is verified with English,Hindi,Malayalam,Japanese. S.Banerjee. Journal of Language and Computation. 5. Problem of Ellipsis in Bangla and its Resolution. The resolution of ellipsis is done in Bangla using higher unification model for computational resolution. The work is being verified with English,Hindi,Malaylam and Japanese. S.Banerjee. Finite String. 6. Syntactic Analysis of the pronominal problems in Bangla. The GB principles are revised to tackle the pronominal problems (R-expressions) in Bangla. S.Banerjee Syntax. 7. Problems of ellipsis in Bangla and its resolution. The problem of ellipsis is tackled using the Higher Unification and other results are verified with English,Hindi,Malyalam and Japanese. S.BanerjeeandS.Bhattacharya. Machine Translation. 8. Stylistics Analysis of Bengali language. The paper analyses and resolves the problems of Stylistics in Bangla. S. Banerjee. Linguistic Inquiry. 9. Problem of Anaphor in Bengali language. Problem of Anaphor is detailed in Bengali language. S.Banerjee.andS.Bhattacharya. Applied Linguistics. 10. Pronominal Analysis of Bengali language. In an unique endeavour it is shown that Bengali language contains 776 pronouns. All are detailed and linguistic and computational problems are analyzed and solved. S.Banerjee. Language. 11. Semantic Analyses of the pronominal problems in Bengali language. A new theory of Semantics is proposed to tackle the theory of pronominals,especially that of Bengali. S.Banerjee Natural Language and Linguistic Theory. 12. Object Oriented Grammar. A New Approach with OOPS technology is done to tackle the problem of Machine Translation.(A short conference of related topic has been published in the TAG+4 Conference in the IRCS,University of Pennsylvania,USA in 1998). S.Banerjee.S.Bhattacharya. IEEE Communicationss 7. BOOKS 1.INTRODUCTION TO COGNITIVE SCIENCE. Abstract: This book deals with the whole range of cognitive science including Linguistics,Philosophy,Statistics,Mathematics,Oriental Studies, Literary Criticism,Computer Science and Logic. The endeavour of this book is blessed by Professor Probal Dasgupta of the University of Hyderabad. 2. LINGUISTIC ENCYCLOPAEDIA. Abstract: Revises the Linguistic Encyclopaedia by David Crystal with examples from Indian and Asian languages. 8.AWARDS a) Invited Speaker on Artificial Intelligence from Indian Statistical Institute,Kolkata in 1997. b) Junior Research Fellowship in Computer Science and Communication Science of Indian Statistical Institute,Kolkata in 1997. c) Member of the Association of the Mathematics of Languages,USA (MOL) from 1998 till date. d) Invited Speaker of the Institute for Research in Cognitive Science (IRCS), Department of Computer Science, University of Pennsylvania, PA, USA in 1998. e) Member of the Center for Advanced Study of India, School of Arts and Sciences, University of Pennsylvania, USA from 1998 to till date. f) Member of the Bengali Linux Forum from 2002. g) Linguistic Adviser to the C-DAC, Kolkata . h) Advisor to the Department of Information Technology, Govt.of West Bengal. i) Advisor to the Linguistic Program, Monash University,Australia. (proposed). j) Proposed Advisor to Satyam Infotech, Hyderabad. k) Proposed Advisor to the NLP Project in CIEFL,Hyderabad. l) Proposed Advisor to the NLP Project in ISI,Kolkata.-CDAC-IITK- Project on Medical Assistance System. m) Proposed Advisor to the Ministry of Information Technology,Government of India. [login to view URL] EXPERIENCE. a) Worked for Five years in the Computer Science Division of the Indian Statistical Institute,Kolkata ([login to view URL]) as a researcher of Natural Language Processing. b) Worked for a period of 6 months or so in Language Technology Research Center, International Institute of Information Technology, Hyderabad ([login to view URL]) under Professor Vineet Chaitanya. c) Working in the Department of Computer Science and Engineering, Indian Institute of Technology, Kanpur ([login to view URL]) as a project scientist for the last one year. 10. EDUCATIONAL QUALIFICATION:PhD in NLP Submitted in Calcutta University recommended for D.Litt.(Anyone may check about the status of this degree in the Calcutta University web site) [login to view URL]. Degree Level Subject Year Institute. 1. MA Masters Applied Linguistics 1997 University of Hyderabad. 2. BA Bachelors Linguistics 1994 University of Calcutta. 11. COMPUTER KNOWLEDGE. a) HLL Known : C,C++,Prolog,Perl. b) O/S Handled : Linux,Unix,Windows,DoS,VAX. c) Machines Handled : DEC-VAX,SunSolaris,AS-400,IBM PC. 13. LANGUAGES KNOWN. READ WRITE SPEAK ENGLISH ENGLISH ENGLISH HINDI HINDI HINDI BENGALI BENGALI BENGALI ASSAMESE ASSAMESE ASSAMESE 14. LANGUAGES INVESTIGATED. Bengali, Hindi, Assamese, Engl
## Area of Expertise
High Level Languages : C, C++. O/S: Unix, Linux,Windows,DoS. Specialisations: 1)NLP based softwares like MT system,tagger,parser,chunker,Q&A Machine, Language Modellings. 2)Operating System. 3)Networking. 4)Cryptography. 5)WEb designing using HTML. 6)Language Translations. 7)Visual Basic Programming.
