Machine Teaching for Information Extraction
Recent work on information extraction has suggested that fast, interactive tools can be highly effective; however, creating a usable system is challenging, and few publically available tools exist. In this paper we present IKE, a new extraction tool that performs fast, interactive bootstrapping to develop high-quality extraction patterns for targeted relations, and provides novel solutions to these usability concerns. In particular, it uses a novel query language that is expressive, easy to understand, and fast to execute - essential requirements for a practical system - and is the first interactive extraction tool to seamlessly integrate symbolic and distributional methods for search. An initial evaluation suggests that relation tables can be populated substantially faster than by manual pattern authoring or using fully automated tools, while retaining accuracy, an important step towards practical knowledge-base construction.