Skip to main content
. Author manuscript; available in PMC: 2017 Mar 22.
Published in final edited form as: SIGMOD Rec. 2016 Feb 6;45(1):60–67.

Figure 4.

Figure 4

One challenge of building high-quality KBC systems is dealing with diverse sources jointly to make predictions. In this example page of a Paleontology journal article, information extracted from tables, text, and external structured knowledge bases are all required to reach the final extraction. This problem becomes even more challenging when many extractors are not 100% accurate, thus motivating the joint probabilistic inference engine inside DeepDive.