Big data techniques for industrial problems with little data

Abstract

Technicians and maintenance managers in industrial environments would benefit from automatically extracting entities and relationships from different text data sources such as logs, event reports, and manuals. Extracting components from pieces of text and classifying them to the right failure type is not trivial in the domain specific setting where the vocabulary has specific meaning to the industry or domain, and labeled data set is very small. In this paper we address how to overcome these challenges in named entity recognition and classification of text, and present a way to improve the model iteratively and quickly. This interaction between components and related failures in the system can be represented in a knowledge graph, which enables further investigations such as Root Cause Analysis and Problem Diagnosis.