TIRTHANKAR DASGUPTA
PhD
Student
Department
of Computer Science and Engineering
Indian Institute of Technology Kharagpur
Kharagpur, West Bengal - 721302, India
Phone: +91-9433852325 begin_of_the_skype_highlightingend_of_the_skype_highlighting
Email: iamtirthankar@gmail.com
[About | Research
|
Education
|
Publications | Work Experience]
About
Welcome to
my homepage! I am a PhD student at
Communication Empowerment Lab, Department of Computer Science and Engineering,
Indian Institute of Technology Kharagpur. My research work is primarily based
on Computational Models of Language Comprehension and Processing. The
title of my PhD dissertation is: Computational models of the organization
and processing of Bangla morphologically complex words in the mental lexicon.
My major work elements include performing different psycholinguistic
experiments like, lexical decision tasks, and cross-modal/masked priming
techniques to understand how words are organized and processed in the human
mind and then apply different computational techniques to model such behavior.
My PhD work is supervised by Prof.
Anupam Basu and is
supported by the fellowship of the Ministry of Human Resource and Development
(MHRD), Govt. of India.
Prior to this, I have obtained my Masters (MS by research) from
the Department of Computer Science and Engineering, Indian Institute of
Technology Kharagpur. My Thesis was titled Development of English to
Indian Sign Language Machine Translation System.
I have been working in the field of Computational Linguistics for about seven
years. I have worked on distributional semantics, latent semantic analysis,
supervised and unsupervised models of morphological analysis and generation,
multiword expression extraction, POS-Tagging, Spell-Checker and have been a
part of the machine translation team at Communication Empowerment Lab, Indian
Institute of Technology Kharagpur.
Apart from Natural Language Processing, I am also
interested in the area of Human Computer Interaction, particularly, in
the field of Assistive Technology. I have worked on the design,
development and evaluation of several technologies in support of people with hearing,
vision and motor impairments.
Along with my academic involvements, I am also
associated with The Society for Natural Language
Technology Research Kolkata
as a Visiting Research Consultant since January 2009, where we are developing a number
of interesting tools and technologies for Bangla language.
Research Interest
Computational Psycholinguistics, Natural Language
Processing, Human Computer Interaction, Assistive Technology
Supervisor: Prof.
Anupam Basu
Education
1)
Currently
pursuing PhD from the Department of Computer science and Engineering,
Indian Institute of Technology, Kharagpur, India. (January 2010- April
2015).
2)
MS in Computer Science and Engineering from Indian Institute
of Technology, Kharagpur, India. (January 2006- February 2008).
3)
B.E in Information Technology form Department of
Information Technology, MCKV Institute of Engineering, Liluah, India. (July 1999-July 2003)
4) Back
Publications
Patents Submitted
1.
Tirthankar Dasgupta, Manjira Sinha and Anupam Basu. "WebSanyog:
A web browser for people with Severely Speech and Motor Impairment (SSMI)"
(Pending).
2.
Tirthankar Dasgupta, Manjira Sinha and Anupam Basu. "An Integrated assistive
framework in Desktop and Tablets for developing applications to improve Quality
of Life (QOL) for people with Severely Speech and Motor Impairment(SSMI)"
(Pending)
Books
3.
Anupam Basu, Tirthankar Dasgupta and Sibansu Mukhopadhyay, "Bhasa-Prayukti:
Bhasabijnan o Prayukti Bisayak Prabandha-Sankalan"
Published by Society for Natural Language Technology Research, Kolkata
4.
Tirthankar Dasgupta and Anupam Basu. "Indian Sign Language
Machine Translation and Lexical Data Acquisition". LAP LAMBERT
Academic Publishers, February 2013 (ISBN: 978-3-659-34906-5).
Journals
under Major/Minor Revision
5.
Tirthankar Dasgupta, Manjira Sinha, and Anupam Basu, "Development of
Applications to Enhance Entertainment and Social Interaction Opportunities for
People with Cerebral Palsy in India",
Journal of Assistive Technology (Taylor & Francis).
6.
Tirthankar Dasgupta, Manjira Sinha, and Anupam Basu, "Development of a web
browsing interface for people with severe speech and motor impairment", Journal of Universal Access in the
Information Society (UAIS), Springer.
7.
Tirthankar
Dasgupta and Anupam Basu, "Empirical Experiments to
Study Compositionality in Bangla Compound Verbs", Journal of Language Resource and
Evaluation (LREV), Springer.
Journal Articles Accepted
8.
Tirthankar Dasgupta, Anupam Basu, Plaban Bhowmick and Pabitra Mitra, "A
Framework for the Automatic Generation of Indian Sign Language",
Journal of Intelligent Systems (JIS), 2010, pp. 125-144.
9.
Tirthankar Dasgupta and Anupam Basu,
"Automatic Transliteration of Indian Language Text to Braille for the
Visually Challenged in India", Information Technology in Developing
Countries (ITDC), International Federation for Information Processing
(IFIP), 2009, Volume 19, Number 3, pp-11-18.
10.
Tirthankar Dasgupta, Manjira Sinha, and Anupam Basu,
"Computational Modeling of Morphological Effects in Bangla Visual Word
Recognition", Journal of Psycholinguistic Research (JOPR), DOI:
10.1007/s10936-014-9302-x.
11.
Manjira Sinha, Tirthankar
Dasgupta, Abhik Jana, and
Anupam Basu, "Design and Development of a Bangla Semantic Lexicon and
an Unsupervised Model of Semantic Similarity Measure", International
Journal of Computer Applications (IJCA), DOI: 10.5120/16588-6297.
12.
Tirthankar Dasgupta, Manjira Sinha and Anupam Basu, "Resource
Creation and Development of an English-Bangla Back Transliteration System",
International Journal of Knowledge-Based and Intelligent Engineering Systems (KES), IOS Press,
2015, (Accepted).
13.
Tirthankar Dasgupta, and Anupam Basu, "Computational
Models of the Lexical Representation of Bangla Compound Words in the Mental
Lexicon", Journal of Psycholinguistic Research (JOPR), Springer,
2015, (Accepted).
Conference Papers
NLP &
Psycholinguistics
9.
Manjira Sinha,Tirthankar Dasgupta, Anupam Basu, "Text Readability in Hindi:
A Comparative Study of Feature Performances Using Support Vectors",
International Conference on Natural Language Processing (ICON), 2014, Goa,
India, (Accepted).
10.
Manjira Sinha, Tirthankar
Dasgupta, and Anupam Basu, Influence of Target Reader
Background and Text Features on Text Readability in Bangla: A Computational
Approach, 25th International Conference on Computational Linguistics (COLING),
(Accepted).
11.
Manjira Sinha, Tirthankar
Dasgupta, and Anupam Basu, Design and Development of
an On-line Computational Framework to Facilitate Language Comprehension
Research on Indian Languages, 9th International Conference on Language
Resources and Evaluation, LREC'14, (Accepted).
12.
Tirthankar Dasgupta, Psycholinguistically Motivated
Computational Models on the Organization and Processing of Morphologically
Complex Words, 51st Annual Meeting of the Association for Computational
Linguistics Proceedings of the Student Research Workshop, ACL'13, pp- 123-129, 2013.
13.
Tirthankar Dasgupta, Manjira Sinha, Anupam Basu, A Joint Source Channel Model for the English to Bengali Back
Transliteration, Mining Intelligence and Knowledge Exploration (MIKE), 2013.
pp. 751-760.
14.
Manjira Sinha, Kaustav
Rudra, Tirthankar Dasgupta and Anupam Basu, How Word Order Affects Sentence
Comprehension in Bangla: A Computational Approach to Bangla, Mining
Intelligence and Knowledge Exploration (MIKE), 2013. pp. 769-779.
15.
Tirthankar Dasgupta, Manjira Sinha, Anupam Basu,
"Computational Models to understand the Access and Representation of
Bangla Polymorphemic Words in the Mental
Lexicon", International Conference on Computational Linguistics (COLING), 2012,
pp-235-244.
16.
Manjira Sinha, Shakshi
Sharma, Tirthankar Dasgupta,
Anupam Basu, "A New Readability Measure of Bangla and Hindi Texts",
International Conference on Computational Linguistics (COLING), 2012,
pp-1141-1150.
17.
Manjira Sinha, Avik
Jana, Tirthankar Dasgupta,
Anupam Basu, "A New Semantic Lexicon and Similarity Measure in
Bangla", International Conference on Computational Linguistics (COLING), Workshop
on Cognitive Aspects of the Lexicon (CogALex-III),
2012, pp-171-182.
18.
Tirthankar Dasgupta, Sibansu Mukherjee, Manjira Sinha, and Anupam Basu, "Compound Verb Identification
in Bangla", International Conference on Computational Linguistics (COLING), Workshop
on South and Southeast Asian Natural Language Processing (SANLP), 2012,
pp-153-162.
19.
Tirthankar Dasgupta, Manjira Sinha, Anupam Basu, "Forward Transliteration of
Dzongkha Text to Braille", International Conference on Computational
Linguistics (COLING), Workshop on Advances in Text Input Mechanisms, 2012,
pp-97-106.
20.
Sibansu Mukhapadyay, Tirthankar Dasgupta and Anupam
Basu, "Development of an Online Repository of Bangla Literary Texts and
its Ontological Representation for Advance Search Options", International
Conference on Language Resources and Evaluation (LREC), Workshop on
Indian Language and Data: Resources and Evaluation (WILDRE), 2012.
21.
Manjira Sinha, Tirthankar
Dasgupta and Anupam Basu, "A Complex Network
Analysis of Syllables in Bangla through SyllableNet",
International Conference on Language Resources and Evaluation (LREC), Workshop on
Indian Language and Data: Resources and Evaluation (WILDRE), 2012.
22.
Tirthankar Dasgupta, Monojit Choudhury, Kalika Bali, Anupam Basu, "Mental Representation and
Access of Polymorphemic Words in Bangla: Evidence
from Cross-modal Priming Experiments", International Conference on Natural
Language Processing (ICON), 2010, pp. 58-67.
23.
Soumya V.B., Monojit Choudhury, Kalika Bali, Tirthankar Dasgupta and Anupam
Basu, "Resource Creation for Training and Testing of Transliteration
Systems for Indian Languages", International Conference on Language
Resources and Evaluation (LREC), 2010, (In Press).
24.
Tirthankar Dasgupta, Anupam Basu, Plaban Bhowmick and Pabitra Mitra, "English to
Indian Sign Language Machine Translation System: A Structure Transfer
Framework", International Conference on Artificial Intelligence (IICAI), 2009, pp.
2055-2070.
25.
Tirthankar Dasgupta, Sandipan Dandapat and Anupam
Basu, "Prototype English-to-Indian Sign Language Machine Translation
System", International Joint Conference on Natural Language Processing (IJCNLP), workshop
on NLP for Less Privileged Languages(NLPLPL), 2008, pp19-26, Hyderabad, India.
26.
Tirthankar Dasgupta, Sambit Shukla, Sandeep Kumar, Sunny
Jain, and Anupam Basu, "Multilingual Multimedia Indian Sign Language
Dictionary Tool", International Joint Conference on Natural Language Processing
(IJCNLP), workshop
on Asian Language Resources(ALR), 2008, pp. 57-64, Hyderabad, India.
HCI &
Assistive Technology
27.
Tirthankar Dasgupta, Manjira Sinha, Anupam Basu, Web Browsing Interface for People with
Severe Speech and Motor Impairment in India, 16th International ACM SIGACCESS
Conference on Computers and Accessibility (ASSETS), 2014, (Accepted).
28.
Tirthankar Dasgupta, Manjira Sinha, Anupam Basu, Development of Accessible Toolset to
Enhance Social Interaction Opportunities for People with Cerebral Palsy in
India, 16th International ACM SIGACCESS Conference on Computers and
Accessibility(ASSETS), 2014, (Accepted).
29.
Manjira Sinha, Tirthankar Dasgupta, Surabhi Agrawal, Sneha Jain, Nidhi Bagaria ,and Anupam Basu, Development of Entertainment and Social Interaction
Applications to improve Quality-of-Life(QOL) of people with cerebral palsy,
IEEE Technological symposium 2014 , TechSym'14,(Accepted). (Awarded the Best
Paper).
30.
Tirthankar Dasgupta, and Anupam Basu,
"A Prototype Machine Translation System from Text-To-Indian Sign
Language", International Conference on Intelligent User Interface (IUI), 2008, pp.
313-316, Gran Canaria, Spain.
31.
Tirthankar Dasgupta, and Anupam Basu, "A Speech Enabled Text to Braille
Transliteration System for the Visually Impaired People in India",
International Conference on Information and Communication Technology and
Development (ICTD), 2009, pp-201-211, Doha, Qatar. (Awarded the Best
Paper).
32.
Tirthankar Dasgupta, Aakash Anuj, Manjira Sinha,
Ritwika Ghose, Anupam Basu,
"VoiceMail Architecture in Desktop and Mobile
Devices for the Blind People" IEEE International Conference on Intelligent
Human Computer Interaction (IHCI), 2012.
33.
Tirthankar Dasgupta, Anupam Basu, Animesh
Das and Promothesh Mondol,
"Design and Evaluation of Bangla Keyboard Layouts", IEEE Students’
Technology Symposium (TechSym), 2010, pp. 248-254.
34.
Ritwika Ghosh, Tirthankar Dasgupta, and Anupam Basu, "Architecture of a Web
Browser for Visually Handicapped People", IEEE Students’ Technology
Symposium (TechSym), 2010, pp. 325-329.
35.
Tirthankar Dasgupta, and Anupam Basu, "Indian Sign Language
Machine Translation System for the Deaf People of India", Alternative and
Augmentative Communication and Assistive Technologies (AACAT), 2009. pp:44-45,
Mumbai, India
36. Back
Scientific Responsibilities
1)
Editor- Bhasa-Prayukti: Bhasabijnan o Prayukti Bisayak Prabandha-Sankalan
2)
Referee- Journal of Language Resource and Evaluation,
Springer
3)
Regional Coordinating Committee Member of Panini
Linguistic Olympiad in India, 2013, 2014.
4)
Workshop Organized-
a)
Workshop on Natural Language Processing 2011;
b)
Workshop on Cognitive Aspects of Natural Interface Design
2012;
c)
Workshop on Language, Cognition and Computation (LCC) 2013.
Work Experience
Research Consultant, Sponsored Research & Industrial Consultancy, IIT
Kharagpur (December 2009 - Till Date)
1)
Cognitively
Motivated Computational Models of Text Comprehension: The goal of this project is
to identify factors responsible for the comprehension of Indian language texts.
The key work involves:
a)
Performing a series of psycholinguistic experiments to model
possible organization and processing of words in the mental lexicon.
b)
Computing word and sentence complexities for Indian
languages.
c)
Extract cognitive features based on which humans comprehend
words, sentences and discourses. These features are then combined to developed
computational models to predict the comprehensibility of a new text.
d)
The project also involves developing the following practical
NLP tools and resources:
i)
Unsupervised word segmentation tool.
ii)
Unsupervised Bangla compound verb identifier.
iii)
Unsupervised Bangla semantic similarity measure.
iv)
Psycholinguistically motivated Bangla
semantic lexicon.
v)
The Bangla SyllableNet and OrthographNet.
2)
WebSanyog: A Web Browser for People with Neuro-Motor
Disorders
3)
An Integrated assistive framework in Desktop and Tablets for
developing applications to improve Quality of Life (QOL) for people with Severely
Speech and Motor Impairment(SSMI)
4)
Development of
Android based Applications on Aakash
5)
An Open Source Web
Browser for the Visually Impaired People
6)
Creating Accessible
Study Materials for the Print Impaired Students
Researcher, Natural
Language Technology Research, Kolkata, India (March2009- December 2009)
1)
English to Bengali Machine Transliteration
2)
Stylometric Analysis of
Literary Text Documents
3)
Bengali Compound Verb Identification
Senior
Project Officer, Communication Empowerment Laboratory, IIT Kharagpur
(January2006 – February2009)
1)
English-To-Indian Sign Language Machine Translation System
2)
Design and Development of an Indian Sign Language Dictionary
Framework
3)
Design and Development of Dzongkha Text to Braille
Transliteration System
4)
Design and Development of Sparsha,
An Indian Language Text to Braille Transliteration System
5)
Design and Development of a File-Reader System for the
Visually Impaired
6)
Development of a 6-Key Braille Keyboard
Junior
Project Officer, Communication Empowerment Laboratory, IIT Kharagpur (October
2004 – December2005)
1)
Design
and Development of Sahaj Shiksha: An educational toolset for children with
Cerebral Palsy