|
|
Dmitri Roussinov
Dmitri
Roussinov |
Interests and Expertise:
Information Systems, Knowledge
Management, Human Language Technologies, Information Retrieval, Internet Search
Engines, Security Informatics, Human Computer Interaction, Databases and more.
Please see my CV for details.
Professional Experience
2008-Current, Senior Lecturer,
Department of Computer and Information Sciences, University of Strathclyde.
2001-2008, Assistant Professor:
Department
of Information Systems, Arizona State University, USA
1999-2001, Assistant Professor: School of
Information Studies, Syracuse University, USA
1996-1999, Graduate Research
Associate: Karl
Eller Graduate School of Management, The University of
1995-1996, Graduate Research Assistant:
Economics
Science Laboratory (chaired by Nobel Prize winner Prof. V. Smith), The
1994-1996, Senior Software
Engineer, Coextant
Systems,
1990-1993, Software Engineer, Nuclear Safety
Institute,
Education
PhD, Information Systems, University of
Arizona, August 1999. Supervisor: McClelland Professor of MIS Dr.
Hsinchun Chen.
Master of Arts,
Economics, Indiana University, August 1995.
Master and
Bachelor of Science, Computer Science, Moscow Institute of Physics and
Technology , 1991.
Publications
Exploring Models for Semantic Category Verification. With O. Turetken. Accepted with minor revisions to Information Systems.
Automated Task Recognition In Multi-Task Learning. With Seiichi Ozawa and Asim Roy. Conditionally
accepted to IEEE Transactions on Neural
Networks.
Roussinov, D., and
Chau, M., Combining Fact Seeking Services on the Web, Journal of Association for Information
Systems (JAIS), 9 (4), article 12,
2008.
Fong, S.W.,
Roussinov, D, and D.B. Skillicorn, Detecting Word Substitutions in Text.
IEEE Transactions on Knowledge and Data
Engineering (TKDE), special issue on Security and Terrorism Informatics, 20(8), 2008, pp. 1067-1076..
Roussinov, D., Fan, W., and
Robles, J., Beyond Keywords: Automated Question Answering on the Web. Communications of the ACM (CACM), 51(9), pp. 60-65, 2008.
Roussinov, D., and O.
Turetken, Semantic Verification in an Online Fact Seeking Environment, ACM Conference on Information and Knowledge
Management, 2007, pp. 71-78, Lisbon, Portugal.
Roussinov, D., Fong, S., and
Skillicorn, D.B., Detecting Word Substitutions: PMI vs. HMM, In the proceedings of 30th Annual
International ACM SIGIR Conference on Research and Development in Information
Retrieval (poster), 23-27 July
2007, Amsterdam, Netherlands.
Roussinov, D., and Muresan,
G., Internet Mining vs. Pseudo Relevance, Proceedings of the Annual Meeting of the American Society for
Information Science and Technology. (ASIST 2007),
Gheorghe Muresan
and Dmitri Roussinov (2006). Where
Do Good Query Terms Come From? Proceedings of the Annual Meeting of the
American Society for Information Science and Technology. (ASIST 2006),
Austin, Texas, November 2006, (HTML).
This paper describes a framework for investigating the quality of
different query expansion approaches, namely pseudo-relevance feedback,
language mode clarity and based on internet mining...
Fong, S., Skillicorn, D.B, and Roussinov, D.,
Measures to Detect Word Substitution in Intercepted
Communication. In proceedings of IEEE Intelligence and Security
Informatics Conference (ISI 2006),
Those who want to conceal the content of their communications can do so
by replacing words that might trigger attention by other words or locutions
that seem more ordinary. We address the problem of discovering such substitutions…
Fong, S., Skillicorn, D.B, and Roussinov, D., Detecting Word Substitution in Adversarial
Communication. In proceedings of Workshop on
Link Analysis, Counterterrorism and Security, SIAM Conference on Data
Mining, April 20-22, 2006, Bethesda, MD
… terrorists and criminals may replace words by other words or
locutions… we consider ways to detect replacements that have similar
frequencies to the original words.
Roussinov, D., Chau., M., Web
Fact Seeking For Business Intelligence: a
Inspired by our exploration of the applicability of automated question
answering (QA) technology to the task of business intelligence and general
design science principle, we advocate a meta approach to the QA (fact seeking)
applications…
Roussinov, D., and Fan, W., Learning Ranking vs. Modeling Relevance,
Hawaii International Conference on System Sciences (HICSS-39).
we have designed a representation scheme, which is based on the
discretized form of the high level statistics of the query term occurrences
(such as tf, df, and document length) rather than individual terms..…
Roussinov, D., Chau., M., Filatova, E., Robles, J., Building on Redundancy: Factoid Question Answering,
Robust Retrieval and the “Other”. In proceedings of TREC 2005, Nov. 15-18, 2005.
We have explored how redundancy based techniques can be used in
improving factoid question answering, definitional questions (“other”), and
robust retrieval…
N.J. Belkin, M. Cole, J. Gwizdka, Y.-L. Li, J.-J. Liu, G. Muresan, D.
Roussinov, C.A. Smith, A. Taylor, X.-J. Yuan. Rutgers Information Interaction Lab at TREC 2005:
Trying HARD. In proceedings
of TREC 2005, Nov. 15-18, 2005. (slides)
Within the structure of the TREC 2005 HARD track guidelines, we
investigated the following hypotheses...
Roussinov, D., and Robles, J., Applying Question Answering Technology to Locating Malevolent
Online Content. Decision Support Systems, 43 (4), 2007,
pp. 1404-1418.
We have empirically compared two classes of technologies capable of
locating potentially malevolent online content: 1) popular keyword searching
and 2) emerging question answering (QA)..…
Roussinov, D. and Chau., M. Web Fact Seeking Meta Engine for Business Information
Needs. The Fifteenth Annual Workshop on Information Technologies and
Systems (WITS'05), (demo session)
Based on the results of our surveys and interviews with business
intelligence practitioners and success of meta search engines, we advocate a
meta approach to automated question answering.
Roussinov, D., Fan, W., and Das Neves, F.A. Semantic
Verification for Fact Seeking Engines. In proceedings of 2005 ACM Conference on Knowledge and Information
Management.
We present the architecture of our web question answering (fact seeking)
system and introduce a novel algorithm to validate semantic categories of the
expected answers..…
Roussinov, D., Fan, W., and Das Neves, F.A. Learning Global
and Local Weighting for Information Retrieval. In proceedings of 2005 ACM Conference on Knowledge and Information
Management.
Roussinov, D., and Fan, W., Discretization Based Learning Approach to
Information Retrieval. In
proceedings of 2005 Conference on Human Language Technologies.
Roussinov, D., Zhao, L., and Fan, W. Mining Context Specific Similarity
Relationships Using The World Wide Web.
In proceedings of 2005 Conference on Human Language Technologies.
We have studied how context specific web corpus can be automatically
created and mined for discovering semantic similarity relationships between
terms (words or phrases)….
Roussinov,
D. and Robles, J. How Question Answering Technology Helps to Locate Malevolent
Online Content. 2005 IEEE Conference on Intelligence and Security Informatics,
We have suggested and empirically evaluated an alternative technology
(automated question answering or QA) capable of locating potentially malevolent
online content…
Cao, J.,
Roussinov, D., Robles, J., Nunamaker, J., Automated Question Answering From Videos: NLP vs.
Pattern Matching, Hawaii International Conference on System Sciences
(HICSS-38).
We have explored the feasibility of automated question answering from
video material…
Roussinov, D. and Robles, J., Ding, Y., Experiments with Web QA System and TREC2004 Questions.
In the proceedings of TREC
conference.
Although, we were able to run only first 91 out of 230 factoid questions
before the submission deadline, we find our result encouraging, and if
interpolated to the entire questions set, would be above the mean performance
on factoid questions.
Roussinov,
D., and Robles, J., Learning Patterns to Answer Open Domain Questions on
the Web. In the proceedings of
27th
Annual International ACM SIGIR Conference on Research and Development in
Information Retrieval,
We present a probabilistic approach to automated question answering on
the Web, based on trainable patterns, answer triangulation and semantic
filtering.
Roussinov,
D., and Robles, J., Self-Learning
Web Question Answering System. In
the proceedings of 2004 World Wide Web
Conference.
We present a probabilistic approach to automated question answering on
the Web, based on pattern matching and answer triangulation.
Roussinov,
D., and Robles, J., Web
Question Answering Through Automatically Learned Patterns. In the proceedings of The Joint Conference on Digital Libraries.
June 7 -11, 2004, Tucson, AZ.
We explore the feasibility of a completely trainable approach to the
automated question answering on the Web.
Roussinov,
D., and Robles, J., Web
Question Answering: Technology and Business Applications. In the proceedings of 2004 American
Conference on Information Systems. August 6 – 8,
We have explored the feasibility of a completely trainable approach to
automated question answering on the Web for the purpose of business
intelligence and other practical applications.
Roussinov,
D., and Zhao, L., Text clustering and summary techniques for CRM message
management, Enterprise
Information Management, 17(6) , 2004, pp. 424-429.
Roussinov,
D., and Zhao, L., Automatic Discovery of Similarity Relationships
through Web Mining, Decision Support Systems, 35, 2003, pp.
149-166.
This work demonstrates how the World Wide Web can be mined in a fully
automated manner for discovering the semantic similarity relationships among
the concepts surfaced during an electronic brainstorming session ...
Roussinov,
D., and Zhao, L., Message
Sense Maker: Engineering a Tool Set for Customer Relationship Management,
Hawaii International Conference on System Sciences
(HICSS-35).
We develop new issue identification techniques based on clustering and
context aware similarity networks to enable managers to discover knowledge in
text messages…
Roussinov, D., and Zhao, L., Making Sense of CRM Messages: an Interactive Toolset,
AIS 2002 Americas Conference on
Information Systems,
We introduce an interactive toolset that can facilitate the exploration
of CRM data semi-automatically ... through a sequence of steps: 1) identifying
descriptive terms, 2) identifying semantic relationships between the terms, and
3) grouping CRM messages into clusters of related issues.
Roussinov,
D., and Chen,
H., "Information
Navigation on the Web by Clustering and Summarizing Query Results,"
Information Processing and Management,
37 (6), 2001, pp. 789-816.
We have explored and evaluated a novel approach to information seeking
that is grounded in the idea of summarizing query results through automated
document clustering...
Roussinov,
D., Crowston,
K., Nilan, M., Kwasnik, B., Cai, J. and Liu, X., "Genre
Based Navigation on the Web," Hawaii
International Conference on System Sciences (HICSS-34).
We report on our ongoing study of using the genre of Web pages to
facilitate information exploration. By genre, we mean socially recognized
regularities of form and purpose in documents (e.g., a letter, a memo, a
research paper)...
Roussinov,
D. and Chen,
H., Document Clustering For Electronic Meetings: An
Experimental Comparison Of Two Techniques, Decision Support Systems, 27 (1-2),
1999, pp. 67-79.
... We report our implementation and comparison of two text clustering
techniques: Ward's clustering and Kohonen's Self-organizing Maps. We have
evaluated how closely clusters produced by a computer resemble those created by
human experts...
Roussinov,
D. and McQuaid,
M., "Information Navigation by Clustering and Summarizing Query
Results," Proceedings of Hawaii International Conference on System Sciences
(HICSS-33),
We have explored and evaluated a novel approach to information seeking
grounded in the idea of summarizing query results through automated document
clustering...
Roussinov,
D., "Information
Foraging Through Automatic Clustering and Summarization: A Self-Organizing
Approach," Doctoral Dissertation, University of
Arizona, August 1999. Advisors: Hsinchun
Chen, Jay Nunamaker, Olivia Sheng.
... This dissertation attempted to determine whether automated
clustering can help to find relevant information by suggesting an innovative
implementation and verifying its potential ability to be of help...
Roussinov,
D., Tolle,
K., Ramsey M., McQuaid,
M., and Chen, H., "Visualizing Internet Search Results with
Adaptive Self-Organizing Maps," Proceedings of ACM SIGIR, August 15- 19, 1999,
Berkeley, CA. (demo)
... Our prototype acts as a visualizing layer between the user and a
commercial Web search engine (AltaVista). Our system summarizes search results
and suggests additional terms for query modification...
Roussinov,
D., Tolle,
K., Ramsey M., and Chen, H.,
"Interactive
Internet Search through Automatic Clustering: an Empirical Study,"
Proceedings of ACM SIGIR, August 15- 19, 1999,
Berkeley, CA. (poster)
... We have developed and empirically evaluated a method of information
seeking (called Adaptive Search) that combines automatic document clustering
and user feedback in a novel way ...
Roussinov,
D., Internet
Search Using Adaptive Visualization, Proceedings of ACM SIGCHI 1999 Conference
on Human Factors in Computing Systems, Doctoral Consortium, May
15-20, 1999, Pittsburgh, PA
... My research in progress on leveraging navigation by interactively
providing the ability to modify the concept maps themselves has led me to
believe that this functionality increases responsiveness to the user and makes
searching more effective. I explored both what adaptive features users perceive
to be most helpful and the overall effect of adaptation on achieving
information seeking goals...
Romano, N., Roussinov, D., Nunamaker, J., and Chen, H.,
"Collaborative Information Retrieval Environment:
Integration of Information Retrieval with Group Support Systems",
Proceedings of Thirty-Second Annual Hawaii International Conference
On System Sciences, January 5 - 8, 1999, Island of Maui.
Our paper describes how user experiences with IR and GSS systems has
shed light onto a promising new area of collaborative research and led to the
development of a prototype that merges the two paradigms into a Collaborative
Information Retrieval Environment (CIRE).
Roussinov,
D. and Chen
H., "A
Scalable Self-organizing Map Algorithm for Textual Classification: A Neural
Network Approach to Thesaurus Generation", in Communication
and Cognition -- Artificial Intelligence, 15 (1-2), 1998, pp.
81-112.
This paper presents research in which we sought to develop a scaleable
textual classification and categorization system based on the Kohonen's
self-organizing feature map (SOM) algorithm. Our proposed data structure and
algorithm took advantage of the sparseness of coordinates in the document input
vectors and reduced the SOM computational complexity by several order of
magnitude.
Roussinov,
D. and Ramsey
M., "Information Forage through Adaptive Visualization", Proceedings of The Third ACM Conference on Digital
Libraries, pp. 303-304,June 23-26, 1998,
We report our research on leveraging
navigation by providing interactively the ability to modify the maps
themselves. We have created and tested a prototype system that builds and
refines in real-time a map of concepts found in Web documents returned by a
commercial search engine.
Teaching at
Strathclyde
CS104 Information and Information Systems
52.475
Multimedia Information Access
CS.926 - Information Retrieval
CS.934 -
Information Sources and Services
CS.929 - Business Intelligence
Past (non ASU) Teaching
Databases
Information Systems Analysis
Advanced Object Oriented Programming in Visual C++ and Java
Data Structures and Algorithms
Professional (non Academic)
Experience
|
|
1988 – 1995, 6+ years of
R&D, Analysis and Design, Algorithms, C++, Pascal, Fortran, Java, VB,
80x86 Assembly Languages |
