| | |
Summary: Recovering from Errors during Programming by
Demonstration
Jiun-Hung Chen and Daniel S. Weld
University of Washington
Seattle, WA 98195, USA
{jhchen,weld}@cs.washington.edu}
ABSTRACT
Many end-users wish to customize their applications, au-
tomating common tasks and routines. Unfortunately, this
automation is difficult today -- users must choose between
brittle macros and complex scripting languages. Program-
ming by demonstration (PBD) offers a middle ground, al-
lowing users to demonstrate a procedure multiple times and
generalizing the requisite behavior with machine learning.
Unfortunately, many PBD systems are almost as brittle as
macro recorders, offering few ways for a user to control
the learning process or correct the demonstrations used as
training examples. This paper presents CHINLE, a system
which automatically constructs PBD systems for applica-
tions based on their interface specification. The resulting
|
