POIROT - Integrated Learning of Web Service Procedures

Abstract

POIROT is an integration framework for combining ma-chine learning mechanisms to learn hierarchical models of web services procedures from a single or very small set of demonstration examples. The system is organized around a shared representation language for communications with a central hypothesis blackboard. Component learning systems share semantic representations of their hypotheses (gener-alizations) and inferences about demonstration traces. To further the process, components may generate learning goals for other learning components. POIROT’s learners or hy-pothesis formers develop workflows that include order de-pendencies, subgoals, and decision criteria for selecting or prioritizing subtasks and service parameters. Hypothesis evaluators, guided by POIROT’s meta-control component, plan experiments to confirm or disconfirm hypotheses ex-tracted from these learning products. Collectively, they cre-ate methods that POIROT can use to reproduce the demon-stration and solve similar problems. After its first phase of development, POIROT has demonstrated it can learn some moderately complex hierarchical task models from semantic traces of user-generated service transaction sequences at a level that is approaching human performance on the same learning task.