We present an approach to learning procedural knowledge by demonstration called similarity-based alignment and generalization. Key to our approach is the ability to induce complex procedure structure (loops and conditional branches) by aligning multiple unannotated demonstrations of a procedure. We present an implemented instance of a similarity-based alignment and generalization algorithm that relies on the known Input-Output Hidden Markov Models, and describe an extension, the SimIOHMM, that significantly improves the algorithm's performance. We present an empirical evaluation that demonstrates our system's scaling performance and quantifies the performance increase obtained through the use of the SimIOHMM extension.
By: Daniel Oblinger; Vittorio Castelli; Tessa Lau; Lawrence D. Bergman
Published in: RC23140 in 2004
LIMITED DISTRIBUTION NOTICE:
This Research Report is available. This report has been submitted for publication outside of IBM and will probably be copyrighted if accepted for publication. It has been issued as a Research Report for early dissemination of its contents. In view of the transfer of copyright to the outside publisher, its distribution outside of IBM prior to publication should be limited to peer communications and specific requests. After outside publication, requests should be filled only by reprints or legally obtained copies of the article (e.g., payment of royalties). I have read and understand this notice and am a member of the scientific community outside or inside of IBM seeking a single copy only.
Questions about this service can be mailed to reports@us.ibm.com .