Formatting by Demonstration: An Interactive Machine Learning Approach

Many routine formatting tasks are subject to patterns. This is especially true of formatting actions performed by users in Excel. Excel has built-in functionality to perform some of these tasks, however their application requires the user to explicitly define logical rules. We show that by using int...

Full description

Saved in:
Bibliographic Details
Published in:International journal of computer applications 2014-01, Vol.86 (18), p.41-47
Main Authors: Tanner, Kesler, Giraud-Carrier, Christophe, R. Olsen Jr, Dan
Format: Article
Language:English
Subjects:
Interactive
Machine learning
Routines
Tasks
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Many routine formatting tasks are subject to patterns. This is especially true of formatting actions performed by users in Excel. Excel has built-in functionality to perform some of these tasks, however their application requires the user to explicitly define logical rules. We show that by using interactive machine learning techniques, such patterns can be learned automatically by iteratively analyzing actions as they are performed by the user. This decreases the amount of work required of the user, and eliminates the necessity of explicitly defining logical rules. Our results show that many useful formatting patterns can be learned with only a few examples.
ISSN:0975-8887
0975-8887
DOI:10.5120/15090-3080