ASKNet: Automated Semantic Knowledge Network

Abstract

The ASKNet system is an attempt to automatically generate large scale semantic knowledge networks from natural language text. State-of-the-art language processing tools, including parsers and semantic analysers, are used to turn input sentences into fragments of semantic network. These network fragments are combined using spreading activation-based algorithms which utilise both lexical and semantic information. The emphasis of the system is on wide-coverage and speed of construction. In this paper we show how a network consisting of over 1.5 million nodes and 3.5 million edges, more than twice as large as any network currently available, can be created in less than 3 days. We believe that the methods proposed here will enable the construction of semantic networks on a scale never seen before, and in doing so reduce the knowledge acquisition bottleneck for AI.