Joint Information Extraction from the Web Using Linked Data

Isabelle Augenstein

Abstract: Almost all of the big name Web companies are currently engaged in building ‘knowledge graphs’ and these are showing significant results in improving search, email, calendaring, etc. Even the largest openly-accessible ones, such as Freebase and Wikidata, are far from complete, partly because new information is emerging so quickly. Most of the missing information is available on Web pages. To access that knowledge and populate knowledge bases, information extraction methods are necessitated. The bottleneck for information extraction systems is obtaining training data to learn classifiers. In this doctoral research, we investigate how existing data in knowledge bases can be used to automatically annotate training data to learn classifiers to in turn extract more data to expand knowledge bases. We discuss our hypotheses, approach, evaluation methods and present preliminary results.