Share Email Print

Proceedings Paper

Task learning from instruction: an application of discourse processing techniques to machine learning
Author(s): John D. Lewis; Bruce Alexander MacDonald
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

A good teacher will provide crucial information about a new task, rather than simply performing examples with no elaboration. Machine learning paradigms have ignored this form of instruction, concentrating on induction over multiple examples, or knowledge-based generalization. This paper presents a model of supervised task learning designed to exploit communicative acts. Instruction is viewed as planned explanation, and plan recognition is applied to the problem at both domain and discourse levels, and extended to allow the learner to have incomplete knowledge. The model includes a domain level plan recognizer and a discourse level plan recognizer that cues a third level of plan structure rewriting rules. The rewriter may add new domain operator schemata. Details are given of an example in which a robot apprentice is instructed in the building of arches.

Paper Details

Date Published: 1 March 1992
PDF: 12 pages
Proc. SPIE 1707, Applications of Artificial Intelligence X: Knowledge-Based Systems, (1 March 1992); doi: 10.1117/12.56883
Show Author Affiliations
John D. Lewis, Univ. of Calgary (Canada)
Bruce Alexander MacDonald, Univ. of Calgary (Canada)

Published in SPIE Proceedings Vol. 1707:
Applications of Artificial Intelligence X: Knowledge-Based Systems
Gautam Biswas, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?