Siddharth Patwardhan

Education

University of Utah, Salt Lake City, UT
Ph.D. (Sep 2009) Major: Computer Science
Dissertation: "Widening the Field of View of Information Extraction through Sentential Event Recognition"
GPA: 3.9 / 4.0

University of Minnesota, Duluth, MN
Master of Science (Aug 2003) Major: Computer Science
Thesis: "Incorporating Dictionary and Corpus Information into a Context Vector Measure of Semantic Relatedness"
GPA: 4.0 / 4.0

Maharashtra Institute of Technology, University of Pune, India
Bachelor of Engineering (May 2001) Major: Computer Science
Final Year Project: "Generic Interface for Designing Embedded Systems"
Result: First Class

Publications

S. Patwardhan and E. Riloff. A Unified Model of Phrasal and Sentential Evidence for Information Extraction. In Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing, pages 151-160, Singapore, August 2009.

Y. Park, S. Patwardhan, K. Visweswariah, and S. Gates. An Empirical Analysis of Word Error Rate and Keyword Error Rate. In Proceedings of the International Conference on Spoken Language Processing, pages 2070-2073, Brisbane, Australia, September 2008.

S. Patwardhan and E. Riloff. Effective Information Extraction with Semantic Affinity Patterns and Relevant Regions. In Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pages 717-727, Prague, Czech Republic, June 2007.

S. Patwardhan, S. Banerjee, and T. Pedersen. UMND1: Unsupervised Word Sense Disambiguation Using Contextual Semantic Relatedness. In SemEval-2007: Proceedings of the 4th International Workshop on Semantic Evaluations, pages 390-393, Prague, Czech Republic, June 2007.

T. Pedersen, S. Pakhomov, S. Patwardhan, and C. Chute. Measures of Semantic Similarity and Relatedness in the Biomedical Domain. Journal of Biomedical Informatics, 40(3):288-299, June 2007.

S. Patwardhan and E. Riloff. Learning Domain-Specific Information Extraction Patterns from the Web. In Proceedings of the ACL 2006 Workshop on Information Extraction Beyond the Document, pages 66-73, Sydney, Australia, July 2006.

E. Riloff, S. Patwardhan, and J. Wiebe. Feature Subsumption for Opinion Analysis. In Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing, pages 440-448, Sydney, Australia, July 2006.

S. Patwardhan and T. Pedersen. Using WordNet-based Context Vectors to Estimate the Semantic Relatedness of Concepts. In Proceedings of the EACL 2006 Workshop on Making Sense of Sense: Bringing Computational Linguistics and Psycholinguistics Together, pages 1-8, Trento, Italy, April 2006.

Y. Choi, C. Cardie, E. Riloff, and S. Patwardhan. Identifying Sources of Opinions with Conditional Random Fields and Extraction Patterns. In Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, pages 355-362, Vancouver, Canada, October 2005.

C. Thompson, S. Patwardhan, and C. Arnold. Generative Models for Semantic Role Labeling. In Proceedings of SENSEVAL-3: Third International Workshop on the Evaluation of Systems for the Semantic Analysis of Text, pages 235-238, Barcelona, Spain, July 2004.

S. Patwardhan. Incorporating Dictionary and Corpus Information into a Context Vector Measure of Semantic Relatedness. Master's thesis, University of Minnesota, Duluth, August 2003.

S. Patwardhan, S. Banerjee, and T. Pedersen. Using Measures of Semantic Relatedness for Word Sense Disambiguation. In Proceedings of the Fourth International Conference on Intelligent Text Processing and Computational Linguistics, pages 241-257, Mexico City, Mexico, February 2003.

Related Experience

Post-doctoral Researcher. Oct 2009 - present
IBM T. J. Watson Research Center, Hawthorne, NY

Am part of a team working on the Jeopardy! Challenge. Design and implement approaches for question analysis employed by the Question Answering system. Also work on a Machine Reading project sponsored by DARPA. Create algorithms for processing text to automatically locate relevant information within documents.
Research Assistant. Aug 2003 - Oct 2009
School of Computing, University of Utah, Salt Lake City, UT

Assisted Dr. Ellen Riloff on various projects in Opinion Analysis and Information Extraction.
- Built a system (funded by LLNL) that improves Information Extraction coverage using rules learned from the Web.
- Created an opinion analysis classification system as part of the AQUAINT project (funded by ARDA).
- Worked with Dr. Cindi Thompson to build a generative-model-based semantic role labeling system.
Summer Research Intern. May 2007 - Aug 2007
IBM T. J. Watson Research Center, Hawthorne, NY

Devised a Web-based algorithm, implemented in Java, for domain-specializing an automatic speech recognition system. The algorithm was implemented as a UIMA compoment that used documents from the Web to train a language model for a specific domain. This project was done under the guidance of Dr. Stephen Gates and Dr. Youngja Park in the Language Engineering for Content Analysis research group.
Summer Research Intern. May 2003 - Aug 2003
Division of Biomedical Informatics, Mayo Clinic, Rochester, MN

Created a collection of Perl modules to measure the semantic similarity of medical concepts, based on the SNOMED-CT® semantic hierarchy and statistics extracted from clinical texts. This work was done under the supervision of Dr. Serguei Pakhomov. Journal article to appear in JBI and published in U.Minn. Digital Technology Center Report DTC 2005/12.
Teaching Assistant. September 2001 - May 2003
Department of Computer Science, University of Minnesota Duluth, Duluth, MN

Designed and prepared course material for undergraduate courses. Graded exams and assignments. Conducted labs and lectures for the courses (Computer Science 1, Natural Language Processing, Operating Systems Practicum).
Research Assistant. June 2002 - August 2002
Transportation Data Research Laboratory, Duluth, MN

Worked with Minnesota Department of Transportation and Traffic Management Center to carry out research on analysis and processing of transportation data. Designed archive structure and wrote software to retrieve and archive data from data sensors. The principle focus of TDRL is to develop a large-scale centralized transportation data center that serves as a transportation information resource for MN/DOT, University researchers, and other government agencies.

Projects

GLACIER Information Extraction System (2007): An IE system that combines global relevance information with local contextual evidence for effective information extraction (coded in C++, presented at the EMNLP-ConLL '07 conference).
Learning IE Patterns from the Web (2006): This system improves the coverage of an existing Information Extraction system by inferring new relevant extraction patterns from the Web (coded in C++, presented at a workshop in the ACL '06 conference).
Subsumption Hierarchy for Opinion Analysis (2006): A hierarchy used for selecting the best combination of features for a text-classification system that detects opinions in text. (coded in C++, presented as a poster at the EMNLP '06 conference).
Opinion Source Identification (2005): A system for identifying opinion-holders in free text, uses lexicosyntactic features in a machine learning system. (coded in C++, part of the OpinionFinder system demonstrated at the EMNLP '05 conference).
Generative Model for Role Labeling (2004): A machine-learning system, trained using FrameNet, for automatically assigning semantic roles to words in text (coded in Java, participated in SENSEVAL-3).
WordNet::SenseRelate (2004): A system that determines the intended meaning of a word from its context using the notion of Semantic Relatedness of concepts. Was demonstrated at ACL '05 and AAAI '05 conferences (coded in Perl, available for download at http://senserelate.sourceforge.net).
Semantic Similarity of Biomedical Concepts (2003): A collection of Perl modules that adapt existing Computational Linguistics research for measuring semantic similarity of words and concepts to the biomedical domain (coded in Perl, an article to appear in the Journal of Biomedical Informatics).
WordNet::Similarity (2003): A group of modules for measuring the semantic similarity or relatedness of English words and concepts. Was under the supervision of Dr. Ted Pedersen. Demonstrated at NAACL '04 and AAAI '04 conferences (coded in Perl, available for download at http://wn-similarity.sourceforge.net).
Generic Interface for Embedded Systems (2001): A Visual-Basic-like programming language for building graphical interfaces for communicating with embedded systems (coded in Java, team of four students, undergraduate degree final-year project).

Service & Awards

Reviewer, The Journal of Artificial Intelligence Research. 2009.

Program Committee, The 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technology. ACL 2008.

Reviewer, The Third North East Colloquium on Artificial Intelligence. NESCAI 2008.

Reviewer, The Second North East Colloquium on Artificial Intelligence. NESCAI 2007.

Session Chair, ACL Workshop on Information Extraction Beyond the Document. ACL 2006.

Graduate Student Advisory Committee. School of Computing, University of Utah, Salt Lake City, UT. Elected 2004 - 2005.

Most Outstanding Teaching Assistant. Graduate School, University of Minnesota Duluth, Duluth, MN. Awarded 2003.

National Talent Search Scolarship. National Council for Educational Research and Training, New Delhi, India. Awarded 1995 - 2001.

Resumé in PDF Format

Resumé in ODF Format