Syed S. Ali
Visiting Assistant Professor & Assistant Scientist
Mathematical Sciences Department
University of Wisconsin-Milwaukee
Phone: (414) 229-4364
Dr. Syed S. Ali is a visiting assistant professor and assistant scientist
in the department of Mathematical Sciences at Science at UW-Milwaukee.
He has been at UWM since August of 1996, and pursues his interests in teaching
(particularly artificial intelligence) and research in knowledge representation,
natural language processing, and computational linguistics.
Syed Ali's Research Activities
Research Interests and
I am interested in computational models for human-computer communication.
I investigate these models by proposing theories and implementing them
in systems. This process has two advantages; first, it permits validation
that the methods are computationally tractable; and
second, it permits evaluation of the models in real-world applications
My current research is concerned with intelligent dialog systems; such
systems should participate in an interactive dialog with a user in much
the same way that people converse with each other. The work is inherently
interdisciplinary, and my recent grant proposals have involved colleagues
from Linguistics, Educational Psychology, and Nursing (the latter
a domain expert).
The specific projects that I am currently involved with include:
The ARGUER project aims
to develop a computational model of argumentation on the basis of information
that characterizes the structure of arguments. The methods being developed
can be used both to detect arguments and to generate candidate arguments
for rebuttal. No assumption of a priori knowledge about attack
and support relations between propositions, advanced by the
agents participating in a dialog, need be made. Most importantly,
the relations are dynamically established while the dialog is taking place.
This allows incremental processing since agents need only consider the
current utterance advanced by the dialog participant, not necessarily the
entire argument, to be able to continue processing.
The B2 project aims to effectively
tutor medical students while communicating with them in a natural and flexible
way. The primary means of instruction is to allow students to set up hypothetical
situations to learn how different factors affect outcomes. B2 supports
mixed-initiative interaction in English and maintains an incremental dialog
model which allows the interpretation of fragmentary utterances as providing
The ColTrain project aims
to research methods for enhancing the ability of people and computer systems
to collaborate in learning and understanding complex information. Collaborative
systems actively help people perform a task, communicating in a natural
and flexible manner. For a computer system to collaborate with a user,
they must learn from each other and adapt their behavior. They must also
be able to communicate, so that they can define goals and negotiate over
how to proceed and how to evaluate their progress. The testbed area for
collaborative learning that we are using is the curriculum of the Blood
Pressure Measurement Education Program, developed by the American Heart
Association (AHA) chapter in Milwaukee.
The PEAS (Patient Education
and Activation System) project aims to prepare people to take a more active
role in health care decisions. The project is investigating strategies
for helping people identify their health care concerns, learn what actions
they can take on their own, and, if necessary, be able to verbalize their
concerns to health care professionals. These strategies combine a multi-modal
computer interface (including typed text and mouse-inputs) with intelligent
tutoring and intelligent discourse processing. As PEAS interacts with a
patient, it will vary the content and pace of the interaction and
suggest relevant learning activities.
The YAG (Yet Another Generator)
project is specifying and building a fast (and hence suitable for interactive
dialog) natural language generation (NLG system that is capable of tailoring
text to user models for any application. YAG employs a template-based
approach. Templates can be ailored to the user model or application
domain. It permits this tailoring by allowing templates to be defined at
many different levels, including yntactic, linguistically-oriented,
templates and semantic, conceptually-oriented, templates.
A incomplete chronological listing of publications is below. Some publications
are available in compressed postscript, Adobe PDF, or HTML.
A more complete listing can be found in my c.v.
"Mixed Depth Representations for Dialog Processing", with Susan McRoy and
Susan Haller, Proceedings of the 20th
annual meeting of the Cognitive Science Society, Madison, WI, August
1-4, 1998. Postscript,
"Interactive Computerized Health Care Education", with Susan W. McRoy and
Alfredo Liu-Perez, to appear (July 1998) in the Journal of the American
Medical Informatics Association. HTML,
Compressed Postscript, Adobe
"Uniform Knowledge Representation for Language Processing in the
B2 System", with Susan McRoy and Susan Haller. Journal of Natural Language
Engineering, 3(3), 1997. PostScript,
"Knowledge Representation for Natural Language Processing in Implemented
Systems", with Lucja Iwanska. Journal of Natural Language Engineering,
"Towards a Model for Dialogic Discourse", with Susan Haller and Susan McRoy,
Spring Symposium on Computational Models for Mixed Initiative Interaction,
Standford, CA, March 1997. PostScript,Adobe
"Knowledge Representation and Inference for Natural Language Processing",
with Lucja Iwanska and Stuart C. Shapiro, International Journal of Expert
Systems, 9(1), 1996.
"Knowledge Representation for Natural Language Processing in Implemented
Systems", AI Magazine, v. 16 (Spring '95) p. 8-9, 1995.
"ANALOG: A Knowledge Representation System for Natural Language Processing",
Systems, Yfantis, E. A. (ed.), 327-332, Kluwer Academic Publishers,
Dordrecht, The Netherlands, 1995. Postscript,
"Recognizing Text Plans", Susan M. Haller and Syed S. Ali, Proceedings
of the Fourth Golden West International Conference on Intelligent Systems,
76--80, ISCA, Raleigh, NC, 1995. Postscript,
"ANALOG: A Logical Language for Natural Language Processing", American
Association for Artificial Intelligence Fall 1994 Symposium Working Notes,
Knowledge Representation for Natural Language Processing, 1--11, November
4--6, 1994, New Orleans. Postscript,
"A Logical Language for Natural Language Processing, Proceedings of
the 10th Biennial Canadian Artificial Intelligence Conference, Banff,
Alberta, Canada, May 16-20, 1994. Postscript,
Logic' for Natural Language Processing and Knowledge Representation",
Ph. D. Thesis, TR 94-01, Department of Computer Science, State University
of New York at Buffalo, January 1994.
A Knowledge Representation and Reasoning System for Natural Language Reasoning,
Proceedings of the Third International SNePS Workshop, July 28-29,
1994, Buffalo, NY. Postscript,
"Towards a Unified AI Formalism", with S. M. Haller and D. Kumar, Proceedings
of the 27th Hawaii International Conference on System Sciences, 92--101,
IEEE Press, Los Alamitos, CA, 1994.
Language Processing Using a Propositional Semantic Network with Structured
Variables", with S. C. Shapiro, Minds and Machines, 3(4), 1993.
Propositional Semantic Network with Structured Variables for Natural Language
Processing", Proceedings of the Sixth Australian Joint Conference
on Artificial Intelligence, Melbourne, Australia, World Scientific,
Subsumption in a Propositional Semantic Network with Structured Variables",
Proceedings of the Sixth Australian Joint Conference on Artificial Intelligence,
Melbourne, Australia, World Scientific, NJ, 1993.
Representation for Noun Phrases and Anaphora", Proceedings of the
Fifteenth Annual Meeting of the Cognitive Science Society, Lawrence
Erlbaum, Hillsdale, NJ, 1993.
"Using Focus for Generating Felicitous Locative Expressions" Susan. M.
Haller and Syed S. Ali, Proceedings of the Third International Conference
on Industrial and Engineering Applications of Artificial Intelligence and
Expert Systems, 472--477, Charleston, S. Carolina, July 1990.
Syed Ali's Teaching Activities
Syed Ali's Other Activities
Due to time constraints, I currently have a very limited range of other
activities. These activities include aerobics, running, weights, and top-rope
Sy Ali (email@example.com)