Vishnu Vyas' Homepage

NLP Scientist
Advanced Development Group, Apixio

Previously :

2008-2010 Research Engineer
Page Optimization and Presentation Sciences, Yahoo! Inc.

2007-2008 M.S Computer Science.
Department of Computer Science, University of Southern California

2002-2006 B.E Computer Science and Engineering
School of Computing, SRM University.

About Me

I did my Bachelors in Engineering, in Computer Science at SRM Engineering College, Chennai, India. Then I worked for sometime at the Center for Artificial. Later I moved to the U.S to complete a masters in Computer Science at the University of Southern California with a specialization in computational linguistics. Now, I currently work in Apixio's Advanced Development Group as a NLP Scientist, making clinical search better. You can check out my resume in pdf format here.

You can email me at me@vishnuvyas.com

Publications

• Vishnu Vyas, Patrick Pantel, Eric Crestan, Helping Editors Choose Better Seed Sets for Entity Expansion. In Proceedings of CIKM 2009, Hong Kong [pdf]
• Patrick Pantel, Eric Crestan, Arkady Borkovsky, Ana-Maria Popescu and Vishnu Vyas, Web-Scale Distributional Similarity applied to Entity Set Expansion.. In Proceedings of EMNLP 2009, Singapore [pdf]
• Vishnu Vyas and Patrick Pantel, Semi-Automatic Entity Set Refinement. In Proceedings of Human Language Technologies: NAACL-2009, p.p. 290-298, Boulder, CO. [pdf]
• Patrick Pantel and Vishnu Vyas, Joint Information Model for n-best Ranking. In Proceedings of COLING 2008, p.p. 661-668, Manchester, U.K [pdf]
• Vishnu Vyas and Patrick Pantel., Explaining Similarity of Terms. In Proceedings of COLING 2008, Manchester, U.K,[pdf]

My advisor at USC was Patrick Pantel and we worked on Computational Lexical Semantics, Large Scale Data Processing and Statistical Methods as applied to Natural Language Processing.

I have also worked with Jafar Adibi and Eduard Hovy on Social Networking and Link Analysis using the Enron Dataset. You can see someof my work on the Enron Email Dataset here (under construction)

Software

• PyInfo - Easy Latex to HTML howto page generator
• A Python library to use Yahoo's BOSS service

Projects

• The Cactus Virtual Machine
• Link analysis on the Enron email dataset
• Automatically Extracted Wikipedia Category Heirarchy

Research Interests

My primary area of interest lies in the intersection of statistical natural language processing and information retrieval. More specifically, I am interested in exploiting natural language technologies to improve information retrieval.

Writing

More sophisticated and technical writing goes here. If you are more interested in my random rabmlings on Life,the universe and everything else, take a look at my blog