James F. Allen, URCS Faculty Member
b. 1950. Ph.D. (1979) University of Toronto. Assistant Professor
(79-84), Associate Professor (84-87), Department Chair (87-90),
Professor (87-present), Dessauer Chair (92-present); University of
Rochester. Editor-in-Chief, Computational Linguistics (83-93;
Presidential Young Investigator (84-89); author of
Natural Language
Understanding, Benjamin Cummings (87), 2nd edition (1995); Reasoning About Plans, Morgan
Kaufmann (91); co-editor of Readings in Planning, Morgan Kaufmann (90);
Fellow of the AAAI.
James Allen's research interests span a range of issues covering
natural language understanding, discourse, knowledge representation,
common-sense reasoning and planning. A paper about the current state
of AI given at the 1998 AAAI conference can be found
here
These areas of research are
combined in the TRAINS project, a long term effort co-directed with
Len Schubert. The TRAINS system is an intelligent planning assistant
that can converse in spoken natural language with a person to create,
discuss and evaluate various plans involving freight shipments by
train. In particular, Allen's research breaks down into two main
subareas, broadly classified as research in discourse and research in
plan reasoning.
The research in discourse is focused on two-person extended dialogs
in which the speakers have specific tasks to accomplish. An emphasis
in this work is the representation and use of the context of the
dialog to solve problems in semantic interpretations and the
recognition of the intentions underlying the speakers' utterances.
Work in this area has included developing the first computational
model of speech acts, the development of a multi-level plan-based
analysis involving discourse-level plans as well as domain-level
plans, and the development of several different discourse-plan
recognition algorithms. In addition, we are exploring how prosody and
intonation signals discourse intentions and how this interacts with
the plan-based dialog model. While it is important for work to be
formally well-defined and understood, it is equally important that
computational theories can lead to effective implementations. As a
result, a considerable amount of effort has also been made in
developing an expressive hybrid knowledge representation system that
can support complex reasoning about plans and actions.
The research in plan reasoning draws much of its motivation from the
dialog work. In particular, the representation of plans must support a
wide range of different forms of reasoning: plan construction (i.e.
traditional planning), plan recognition, plan evaluation, and the
communication of plans between agents. Much of our work in this area
has focused on the representation of time and action, and we have
reformulated the planning problem as a problem in temporal reasoning.
Within this framework, we have developed a representation of plans
that is temporally explicit and supports plan construction,
recognition and communication. We are also exploring methods of
temporal reasoning that are viable even with large data sets of
temporal information.
Selected Publications on Temporal Reasoning
- Allen, J.F. ``Maintaining Knowledge about Temporal Intervals.''
Communications of the ACM 26, 11, 832-843, November 1983.
- Allen, J.F. ``A General Model of Action and Time.'' Artificial
Intelligence 23, 2, July 1984.
- Allen, J.F. and P.J. Hayes. ``Moments and Points in an
Interval-Based Temporal Logic.'' Computational Intelligence,
January 1990.
- Allen, J.F.
"Time and time again: The many ways to represent time," Int'l. Jr. of Intelligent Systems 6, 4, 341-356, July 1991.
- Allen, J.F. and Ferguson, G. Actions and Events in Interval Temporal Logic, J. Logic and Computation 4, 5, 1994.
Selected Publications in Planning and Plan Recognition
- Kautz, H. and Allen, J.F. "Generalized Plan Recognition" In Proc., Proc., AAAI Nat'l. Conf. on Artificial Intelligence, Philadelphia, PA, 1986
- Allen, J.F. Planning as Temporal Reasoning. In Proc., 2nd
Principles of Knowledge Representation and Reasoning, Morgan
Kaufmann, 1991.
- Allen, J.F. et al. Reasoning About Plans, Morgan Kaufmann, 1991.
- George Ferguson, James Allen, and Brad Miller, TRAINS-95: Towards a Mixed-Initiative Planning Assistant
Proc. Third Conference on Artificial Intelligence Planning Systems (AIPS-96), Edinburgh, Scotland, 29-31 May, 1996, 70-77.
Selected Publications in Natural Language and Dialogue
- Allen, J.F. Natural Language
Understanding, Benjamin Cummings, 1987, Second Edition, 1994.
- Allen, J.F. ``Natural Language, Knowledge Representation and
Logical Form.'' In M. Bates, R. Weischedel (eds.), Challenges in
Natural Language Processing, Cambridge University Press, 1993.
- Allen, J.F. and D.J. Litman. ``A Plan Recognition Model for
Subdialogues in Conversations.'' Cognitive Science 11, 2,
163-200, 1987.
- Allen, J.F. and D.J. Litman. ``Discourse Processing and Common sense Plans.'' in P.R. Cohen, J. Morgan, and M. Pollack, Intentions and Communication, MIT Press, 1990.
- Hinkelman, E. and J.F. Allen. ``Two Constraints on Speech Act
Ambiguity.'' In Proc., 27th Meeting of the Assoc. for
Computational Linguistics, 1989.
- A study on prosody and discourse structure in cooperative dialogs (with S. Nakajima), Phonetica, 1993.
- Traum, D. and Allen, J.F. "Discourse Obligations in Dialogue Processing" Proc. 32nd Meeting of the Assoc. for Computational Linguistics, 1994.
- Allen, J.F. et al, The TRAINS Project: A Case Study in Defining a Conversational Planning Agent, Journal of Experimental and Theoretical AI, 1995.
- Allen, J.F., B. Miller, E. Ringger and T. Sikorski A Robust System for Natural Spoken Dialogue, Proc. 34th Meeting of the Assoc. for Computational Linguistics, 1996.
- Heeman, P. and Allen, J.F. Intonational Boundaries, Speech Repairs and Discourse Markers: Modeling Spoken Dialog, Proc. 35th Meeting of the Assoc. for Computational Linguistics, 1997.
-
George Ferguson and James F. Allen, TRIPS: An Integrated Intelligent Problem-Solving Assistant, Proceedings of the Fifteenth National Conference on AI (AAAI-98), Madison, WI, 26--30 July, 1998.
-
Peter Heeman and James Allen,
Speech Repairs, Intonational Phrases and Discourse Markers: Modeling Speakers' Utterances in Spoken Dialog, Computational Linguistics, Vol. 25-4, 1999.
-
Allen, J., Byron, D., Dzikovska, M., Ferguson, G., Galescu, L. and Stent, A.,
Towards a Generic Dialogue Shell, Natural Language Engineering,6(3) 2000. pp1-16
-
James Allen, Donna Byron, Myroslava Dzikovska, George Ferguson,
Lucian Galescu, and Amanda Stent,
"Towards Conversational Human-Computer Interaction,"
AI Magazine, 2001.
[PDF]
-
James Allen, George Ferguson, and Amanda Stent,
"An architecture for more realistic conversational systems,"
in Proceedings of Intelligent User Interfaces 2001 (IUI-01),
pages 1-8, Santa Fe, NM, January 14-17, 2001.
[PDF]
Software Available
I have two parsing systems available, both in Common Lisp.
The first is a basic parser
written to illustrate the bottom up parsing algorithms in
Natural Language Understanding, Second Edition.
It is designed to be as simple as possible, so it can be used by
students to try the grammars in the book, develop their own small grammars,
and to program extensions to the parser.
The second is the parser from the TRAINS system, which is also a bottom-up chart parser that closely follows Natural Language Understanding, Second Edition, but is written more for efficiency and has additional capabilities that help
construct larger scale grammars. The Users Manual gives more
information on this system and instructions on how to obtain it.
Back to URCS Faculty directory
Back to URCS Home Page