Publication
Continuous Partial Order Planning for Multichannel Document Analysis: A Process-Driven Approach
Kristin Stamm; Marcus Liwicki; Andreas Dengel
In: Proceedings ICDAR 2013. International Conference on Document Analysis and Recognition (ICDAR), Washington D.C. USA, Pages 626-630, IEEE, 8/2013.
Abstract
Abstract—With the rise of email communication, enterprises
strive to manage incoming documents from all input channels
for achieving customer satisfaction. Their overall goal is to
reduce request processing time and to increase processing quality.
Previously, we proposed the approach of process-driven document
analysis (DA) using the concepts of Attentive Tasks (ATs)
and the Specialist Board (SB). The ATs formalize information
expectations of the processes toward an incoming document,
whereas the SB describes all available DA methods. Here, we
propose to apply continuous partial order planning (CPOP) from
machine learning for guiding DA with the goal optimal extraction
accuracy and runtime. To our knowledge, this approach provides
a novel method to integrate knowledge management with DA, in
particular for processes. Since planning has not been applied
to this field yet, we explore learning the suitability function
(SF) and the adaptation of the DA plan. For SF optimization
we propose: (1) Suitability measures of runtime, accuracy, and
their combination and (2) offline, online, as well as off- +
online suitability learning. For planning adaptation strategies we
examine: (1) one-time goal setting, (2) continuous current state,
and (3) continuous goal adaptation. First evaluations indicate the
applicability of the approach and preferences for calibration.