Tomek Strzalkowski, Ph.D. (Simon Fraser University, 1986)

Associate Professor, Computer Science, SUNY Albany

LI-96A, 1400 Washington Ave, Albany NY 12222

Director, Institute for Informatics, Logics & Security Studies

SS-262B, 1400 Washington Ave., Albany, NY 12222

Phone: +518-442-2608

Fax: +518-442-2606

tomek@csc.albany.edu

Research

My research interests are in natural language processing (NLP) and information processing and retrieval (IR). I have been doing work in the following areas:

¨ Computational Linguistics: robust text processing, information extraction, fast parsing, semantic analysis and discourse processing.

¨ Information Retrieval: automated indexing, linguistic indexing, topic detection and tracking, spoken language filtering and retrieval, cross-lingual retrieval, interactive IR.

¨ Automated Summarization: automated abstracting, multi-document summarization.

¨ Open-Domain Question-Answering: automated question answering from unstructured data.

¨ Interactive Dialogue Systems: dialogue modeling, spoken-language dialogues, human-machine conversation, semantics of automated dialogue, automated call centers.

¨ Knowledge Acquisition: corpus analysis, text mining, machine learning.

¨ Logic Programming: Logic grammars, reversible grammars.

¨ Artificial Intelligence: meaning representation.

¨ Institute for Informatics, Logics & Security Studies (ILS). I’m co-director (with Neil Murray) of this cross-disciplinary institute devoted to research and education in computational informatics. ILS is also home of the Natural Language Information Processing Laboratory. More detailed information on some of the projects below can be found at NLIP lab website.

¨ HITIQA: High-Quality Interactive Question Answering. This 2-year project is the first phase of the AQUAINT Program sponsored by the Advanced Research & Development Activity (ARDA). We are developing automated question-answering technology to assist intelligence analyst daily activities.

¨ AMITIES: Automated Multilingual Interaction with Information and Services. This multi-year project is funded jointly by the European Commission and the Defense Advanced Research Projects Agency (DARPA). Along with other partners of the trans-Atlantic consortium, we are developing automated multilingual call center applications through cutting-edge research into speech and natural language processing. ILS partners on AMITIES include University of Sheffield, CNRS-LIMSI, Duke University, VECSYS and General Electric.

¨ XDoX: Cross-Document Summarizer. This project is a continuation of TIPSTER 3 contract, originally funded by DARPA since 1996, continued under ARDA funding, and since 2000 as a subcontract to GE R&D Center. We are developing automated multi-document summarization applications for intelligence analysts.

¨ Natural Language Information Retrieval. This project started in 1992 at New York University has developed techniques for improving text indexing and retrieval using natural language processing techniques. Many organizations participated in this effort, including NYU, GE CR&D, Rutgers, University of Pennsylvania, SRI, University of Helsinki, SICS, and Lockheed Martin.

¨ Document Understanding Conference (DUC). This is an annual formal evaluation conference for text summarization. Sponsored by NIST and DARPA as part of the TIDES Program.

Teaching

In Fall 2002 I’m teaching the following graduate course:

¨ CSI 660 Information Retrieval

o Thursday 1:00pm—4:00pm

o East Seminar Room, CETL

Some Interesting Links

¨ ARDA: Advanced Research & Development Activity

¨ DARPA: Defense Advanced Research Projects Agency

¨ Text Retrieval Conference (TREC)

¨ Association for Computational Linguistics (ACL)

¨ Princeton’s WordNet Lexical Database

¨ Chinese-English on-line dictionary

¨ WebCT Albany homepage

¨ SMART Information Retrieval System

¨ Human-Computer Conversation

Selected Publications

¨ T. Strzalkowski & S. Harabagiu (eds.) Advances in Open-Domain Question Answering. Kluwer Academic Publishers, 2003 (in preparation).

¨ H. Hardy, N. Shimizu, T. Strzalkowski, L. Ting, B. Wise and X. Zhang (2002). Cross-Document Summarization by Concept Classification. Proceedings of SIGIR-2002 Conference, Tampere, Finland.

¨ Information Retrieval and Natural Language Processing, with E. Tzukermann, J. Klavans, in R. Mitkov (ed.), Handbook of Computational Linguistics, Oxford University Press, 2002.

¨ H. Hardy, N. Shimizu, T. Strzalkowski, L. Ting, X. Zhang and B. Wise (2001). Cross-Document Summarization by Concept Classification, Document Understanding Conference, a SIGIR’01 workshop, New Orleans, LA.

¨ The Dialogue Game: Designing Task-Oriented Spontaneous Dialogue System for Automated Call Centers. Invited presentation at 3^rd International Workshop on Human-Computer Conversation, Bellagio, Italy, 2000.

¨ Natural Language Information Retrieval: Progress Report, with J. Perez-Carballo, Information Processing & Management, vol. 36, no. 1, pp. 155-178. 2000.

¨ PartsID: A Dialogue-Based System for Finding Parts for Medical Systems, with A. Bagga, and B. Wise, in Proceedings of 6th Applied Natural Language Conference (ANLP-2000), Seattle, WA, May, 2000

¨ Towards the Next Generation Information Retrieval, in Proceedings of the RIAO-2000, 6th International Conference on Intelligent Multimedia, Information Retrieval Systems and Management, Paris, April, 2000.

¨ Natural Language Information Retrieval. Kluwer Academic Publishers, 1999.

¨ Robust Practical Text Summarization, with G. Stein, J. Wang, B. Wise, in Advances in Automatic Text Summarization, MIT Press, 1999.

¨ A Robust, Lightweight Topic Tracking System, with G. Stein and G.G. Wise, in Proceedings of DARPA Broadcast News Workshop, Herndon Va. 1999.

¨ Summarization-based Query Expansion in Information Retrieval, with J. Wang and B. Wise, in Proceedings of Coling—ACL'98, Montreal. 1998.

¨ A Robust, Practical Text Summarization, with J. Wang, and B. Wise, in Proceedings of AAAI Spring Symposium, Stanford University, 1998.

¨ Robust Text Processing in Automated Information Retrieval, in K. Sparck-Jones and P. Willet (eds.) Readings in Information Retrieval, Morgan Kaufman Publishers, pp. 317-322, 1997.

¨ A Natural Language Correction Model for Continuous Speech Recognition, with R. Brandow, in Proceedings of 5^th Workshop on Very Large Corpora (WVVLC-5), Beijing-Hong Kong, 1997.

¨ Evaluation of TTP parser: A Revised Report, with P. Scheyen in H. Bunt & M. Tomita (eds.) Recent Advances in Parsing Technology, Kluwer Academic Publishers, pp. 201-220, 1996.

¨ Natural Language Information Retrieval, in Information Processing Management. vol. 31, no. 3, pp. 397-417. 1995.

¨ A Self-Learning Universal Concept Spotter, with J. Wang, in Proceedings of Coling-96, Copenhagen, Denmark, 1996, pp. 931-936.

¨ Reversible Grammar in Natural Language Processing, in Kluwer Academic Publishers, 1994

¨ A Fast and Robust Parser for Natural Language, in 14th International Conference on Computational Linguistics (COLING'92), Nantes, France, 1992, pp. 198-204.

¨ Reversible Logic Grammars For Natural Language Parsing and Generation, in Computational Intelligence, pp. 145-171. National Research Council of Canada, 1990.

¨ Automated inversion of logic grammars for generation, with P. Peng in 28th Annual Meeting of the ACL, Pittsburgh, PA, June 1990, pp. 212-219.

¨ Non-Singular Concepts in Natural Language Discourse, with N. Cercone in Computational Linguistics, MIT Press, pp. 171-187, 1989.

¨ A Framework for Computing Extra-Sentential References, with N. Cercone in Computational Intelligence, 2(4), National Research Council of Canada, pp. 159-179, 1986.

¨ Transformation of Natural Language into Logical Formulas, with L. Bolc in 9th International Conference on Computational Linguistics (COLING), Prague, Czechoslovakia, 1982. pp. 29-36.