Home Page of Sudeshna Sarkar

বাংলা পাতা

Computer Science & Engineering Department
Head, Centre for Artificial Intelligence
Indian Institute of Technology Kharagpur
WB, India 721302

B.Tech, 1989, IIT Kharagpur
M.S., 1991, University of California, Berkeley
Ph.D., 1996, IIT Kharagpur
Sudeshna Photo

Email: sudeshna @ cse . iitkgp . ac . in, shudeshna @ gmail . com,
Office phone: 03222-282256
Fax: 03222-278985


Positions in the Centre for Artificial  Intelligence

  1. Engineering Manager
  2. Developer

Apply by sending resume to coeai.iitkgp@gmail.com

Research Positions

We are looking for students interested in novel applications of Artificial Intelligence and Natural Language Processing.

Some of the domains we are exploring joint research opportunities with different organizations are:

  1. Application of AI in industrial plant operations, for example, prognostics, diagnostics, and throughput and process optimization.
  2. Multi-lingual and cross-lingual methodologies to develop Natural language processing tools in Indian languages.
  3. Integrated Information System and Knowledge Discovery Platform for oil and gas exploration which will involve knowledge representation and machine learning
  4. Using data of natural resources and various rural and other government schemes and use them for innovative solutions in social good.
The following research projects have been undertaken by us and we are looking for more people to join us.
  1. Drug Repurposing through Literature and Patent Mining 
  2. UAY Scheme Sponsors: MHRD, Deity, Excelra
  3. Project under IMPRINT:
  4. A platform for Crosslingual and Multilingual Event Monitoring in Indian Languages 
  5. Research Partnership with Capillary Technologies Pte Ltd
  6. Actionanble Insights by Data Analytics on Retailer Sales Data 

Research Interests

My broad topics of interest span different areas of artificial intelligence and machine learning. My current interests are in text mining and natural language processing, machine learning applications to data and recommender systems. I am mainly interested in building large scale practical systems that can be used to solve real life problems. I wish to make use of natural language understanding and information extraction methodologies for effective information retrieval and content recommendation. I also have a special interest in developing technologies for Indian languages and working with multilingual issues.

Machine Learning

We have been working on Machine Learning methods suitable for different applications in several domains.

Natural Language Processing

We use machine learning to develop NLP modules for Indian languages and low resource languages. We are currently working on syntactic and semantic parsers for some Indian and low resource languages using neural network based parsers and applying crosslingual and multilingual methods. We are also interested in working on machine translation involving low resource languages.

Text Mining

Text mining refers to identifying interesting patterns and  extracting useful information and knowledge from natural language text data. My current interest involves working on the following domains.
  1. Biomedical Domain:
    1.  Extracting entities and relations and from Pubmed, patents, clinical data, blogs
    2. Analysis of interaction networks of heterogeneous entities and biological pathways
  2. Multilingual News Documents
  3. News event extraction, linking and summarization, natural language generation and visualization <\ol>
  4. Text mining of Product Reviews in ecommerce sites

Recommender Systems

  1. Algorithms for recommendation of products based on content, reviews and collaborative filtering
  2. Machine learning algorithms for Campaign Design for ecommerce companies and retailers.
  3. Review recommendation

Ongoing Research Projects

For more details, look at my Research page.

Home Page of Sudeshna Sarkar  (with Menu)