Task learning by instruction in tailor

ABSTRACT

In order for intelligent systems to be applicable in a wide range of situations, end users must be able to modify their task descriptions. We introduce Tailor, a system that allows users to modify task information through instruction. In this approach, the user enters a short sentence to describe the desired change. The system maps the sentence into valid, plausible modifications and checks for unexpected side-effects they may have, working interactively with the user throughout the process. We conducted preliminary tests in which subjects used Tailor to make modifications to domains drawn from the eHow website, applying modifications posted by readers as 'tips'. In this way the subjects acted as interpreters between Tailor and the human-generated descriptions of modifications. Almost all the subjects were able to make all modifications to the process descriptions with Tailor, indicating that the interpreter role is quite natural for users.

REFERENCES

• 1: Blythe, J. Integrating Expectations from Different Sources to Help End Users to Acquire Procedural Knowledge, in Proceedings of IJCAI '01 (2001).
• 2: Jim Blythe , Yolanda Gil, Incremental formalization of document annotations through ontology-based paraphrasing, Proceedings of the 13th international conference on World Wide Web, May 17-20, 2004, New York, NY, USA [doi>10.1145/988672.988734]
• 3: Jim Blythe , Jihie Kim , Surya Ramachandran , Yolanda Gil, An integrated environment for knowledge acquisition, Proceedings of the 6th international conference on Intelligent user interfaces, p.13-20, January 14-17, 2001, Santa Fe, New Mexico, United States [doi>10.1145/359784.359819]
• 4: Fellbaum, C. (ed.) Wordnet: an Electronic Lexical Database, MIT Press, May 1998.
• 5: Huffman, S. and Laird, J. Flexibly Instructable Agents, Journal of AI Research, 3, 1995.
• 6: Jihie Kim , Yolanda Gil, Deriving expectations to guide knowledge base creation, Proceedings of the sixteenth national conference on Artificial intelligence and the eleventh Innovative applications of artificial intelligence conference innovative applications of artificial intelligence, p.235-241, July 18-22, 1999, Orlando, Florida, United States
• 7: Klein, D. and Manning, C. Fast Exact Inference with a Factored Model for Natural Language Parsing, in Proceedings of NIPS '02 (2002).
• 8: Tessa Lau , Lawrence Bergman , Vittorio Castelli , Daniel Oblinger, Sheepdog: learning procedures for technical support, Proceedings of the 9th international conference on Intelligent user interface, January 13-16, 2004, Funchal, Madeira, Portugal [doi>10.1145/964442.964464]
• 9: Lieberman, H. (ed.) Your Wish is My Command, Morgan Kaufmann, San Francisco, 2001.
• 10: David Morley , Karen Myers, The SPARK Agent Framework, Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, p.714-721, July 19-23, 2004, New York, New York [doi>10.1109/AAMAS.2004.267]
• 11: Myers, K. Planning with Conflicting Advice, in Proceedings of AIPS '00 (2000).
• 12: Ana-Maria Popescu , Oren Etzioni , Henry Kautz, Towards a theory of natural language interfaces to databases, Proceedings of the 8th international conference on Intelligent user interfaces, January 12-15, 2003, Miami, Florida, USA [doi>10.1145/604045.604070]
• 13: Alexander Yates , Oren Etzioni , Daniel Weld, A reliable natural language interface to household appliances, Proceedings of the 8th international conference on Intelligent user interfaces, January 12-15, 2003, Miami, Florida, USA [doi>10.1145/604045.604075]

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.6 Learning
          Subjects: Knowledge acquisition

Additional Classification:
  H. Information Systems
  H.5 INFORMATION INTERFACES AND PRESENTATION (I.7)
      H.5.2 User Interfaces (D.2.2, H.1.2, I.3.6)
          Subjects: Interaction styles (e.g., commands, menus, forms, direct manipulation)

General Terms:
Design, Experimentation, Human Factors

Keywords:
knowledge acquisition, reasoning about actions, task learning by instruction