Relevance and Importance in Deep Learning for Open Source Data Processing to Enhance Context

Using information quality attributes to characterize and measure the information quality is necessary to ensure the successful soft and hard data fusion outcome, especially when fusing data of often poor quality such as most of open source data. This paper presents a set of deep learning natural language processing methods for extracting information from open source data which incorporates the information quality attributes, relevance and importance, in a soft and hard information fusion system for decision support so as to enhance context of open source data. The methods are applied and evaluated in the context of maritime situation understanding.