Journal of Logic and Computation Advance Access originally published online on December 20, 2007
Journal of Logic and Computation 2008 18(3):475-493; doi:10.1093/logcom/exm071
Original Articles |
Utilizing Natural Language for One-Shot Task Learning
Florida Institute for Human and Machine Cognition, Pensacola, FL 32502, USA. E-mail: hjung{at}ihmc.us, jallen{at}ihmc.us, lgalescu{at}ihmc.us
Department of Computer Science, Stanford University, Stanford, CA 94305, USA E-mail: natec{at}stanford.edu
Computer Science Department, University of Rochester, Rochester, NY 14627, USA. E-mail: swift{at}cs.rochester.edu
Florida Institute for Human and Machine Cognition, Pensacola, FL 32502, USA. E-mail: wtaysom{at}ihmc.us
Received 31 July 2006.
Learning tasks from a single demonstration presents a significant challenge because the observed sequence is specific to the current situation and is inherently an incomplete representation of the procedure. Observation-based machine-learning techniques are not effective without multiple examples. However, when a demonstration is accompanied by natural language explanation, the language provides a rich source of information about the relationships between the steps in the procedure and the decision-making processes that led to them. In this article, we present a one-shot task learning system built on TRIPS, a dialogue-based collaborative problem solving system, and show how natural language understanding can be used for effective one-shot task learning.
References
- Allen J, Blaylock N, Ferguson G. A problem solving model for collaborative agents. In: Proceedings of the International Joint Conference on Autonomous Agents and Multi-Agent Systems (2002) New York, NY, USA: ACM Press.
- Angros R, Johnson L, Rickel J, Scholer A. Learning domain knowledge for teaching procedural skills. In: Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems (2002) New York, NY, USA: ACM Press.
- Blythe J. Task learning by instruction in tailor. In: Proceedings of the International Conference on Intelligent User Interfaces (2005) New York, NY, USA: ACM Press.
- Chambers N, Allen J, Galescu L, Jung H, Taysom W. Using semantics to identify web objects. In: Proceedings of the National Conference on Artificial Intelligence (2006) Menlo Park, CA, USA: AAAI Press.
- Copestake, Flickinger D. An open source grammar development environment and broad-coverage English grammar using HPSG (2000) Proceedings of the Second International Workshop on Language Resources and Evaluation: ELDA, Paris, France.
- Dzikovska M, Allen J, Swift M. Linking semantic and knowledge representations in a multi-domain dialogue system. Journal of Logic and Computation. Oxford, UK: Oxford University Press. in press.
- Ferguson G, Allen J. TRIPS: an integrated intelligent problem-solving assistant. In: Proceedings of the National Conference on Artificial Intelligence (1998) Menlo Park, CA, USA: AAAI Press.
- Garland, Ryall K, Rich C. Learning hierarchical task models by defining and refining examples. In: Proceedings of the International Conference on Knowledge Capture (2001) New York, NY, USA: ACM Press.
- Gil Y, Blythe J, Kimand J, Ramachandran S. Acquring procedural knowledge in EXPECT (2000) Proceedings of AAAI Fall Symposium. Menlo Park, CA, USA: AAAI Press.
- Lau T, Bergman L, Castelliand V, Oblinger D. Sheep Dog: learning procedures for technical support. In: Proceedings of the International Conference on Intelligent User Interface (2004) New York, NY, USA: ACM Press.
- Lau T, Weld D. Programming by demonstration: an inductive learning formulation (1999) Proceedings of the International Conference on Intelligent User Interfaces. New York, NY, USA: ACM Press.
- Lee F, Anderson J. Learning to act: acquisition and optimization of procedural skill. In: Proceedings of the Annual Conference of the Cognitive Science Society (1997) Hove, UK: Psychology Press.
- Lent M, Laird J. Learning procedural knowledge through observation. In: Proceedings of the International Conference on Knowledge Capture (2001) New York, NY, USA: ACM Press.
- Maxwell J, Kaplan R. An efficient parser for LFG. In: Proceedings of the First Lexical Functional Grammar Conference (1996) Chicago, IL, USA: University of Chicago Press.
- Nicolescu M, Mataric M. Experienced-based representation construction: learning from human and robot teachers. In: Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (2001) Los Alamitos, CA, USA: IEEE Computer Society.
- Rayner M, Hockey BA, Dowding G. Grammar specialization meets language modelling. In: Proceedings of the 7th International Conference on Spoken Language Processing (2002) Bonn, Germany: ISCA Archive.
- Seneff S. TINA: a natural language system for spoken language applications. In: Computational Linguistics (1992) 18. MA, USA: MIT Press. 61–86.
- Yang Q, Wu K, Jiang Y. Learning action models from plan examples with incomplete knowledge. In: Proceedings of the International Conference on Automated Planning and Scheduling (2005) Menlo Park, USA: AAAI Press.
CiteULike 
Connotea 
Del.icio.us What's this?
| ||||||||||||||||||||||||||||||||||||||||||||||||