Consolidating Entity Information from Heterogeneous Text Sources for Multi-INT Fusion

Machine Learning has proven to be a useful approach for developing entity consolidation systems that can be tuned to a particular domain. However, the accuracy of learning algorithms often suffers in applications where there are special cases that learning algorithms systematically misclassify.  To address this, we propose a new twist to the machine learning approach to entity consolidation in which a domain expert provides knowledge to the system about special cases. This knowledge enables the system to create models that explicitly handle these types of cases.   In a sense, our approach combines the best aspects of machine learning with ideas from the older rule-based approach to entity consolidation. The objective is to take advantage of the statistical characteristics of data sets, while making it easy to create commonsense inference models that can utilize these statistics for high accuracy matching. We believe this approach will significantly improve upon the state-of-the-art accuracy of entity consolidation, particularly for applications that involve heterogeneous data, where special cases are more common. BENEFIT: The goal of this project is to develop a very high-accuracy entity consolidation system for aggregating entity data from multiple heterogeneous sources.  In order to make sense of data collected from different sources, it is necessary to understand which entities are being referred to in each document.   Entity consolidation systems are intended to solve this problem, but it can be difficult because two documents may refer to the same entity using somewhat different terms.  Also, sometimes two different entities have the same name.  The work in this project addresses many of these difficult problems, so that entity consolidation can be done with high accuracy.   Fetch Technologies is currently working with numerous customers in the background screening industry, the news industry, and various business intelligence markets that are interested in aggregating information about people, companies, locations, and other entities.  In addition, Fetch also is currently working with government customers that are highly desirous of developing advanced data aggregation capabilities as well