Ontology-driven Question Answering in AquaLog
The semantic web vision is one in which rich, ontology-based semantic markup is widely available, both to enable sophisticated interoperability among agents and to support human web users in locating and making sense of informa-tion. The availability of semantic markup on the web also opens the way to novel, sophisticated forms of question answering. AquaLog is a portable question-answering system which takes queries expressed in natural language and an ontol-ogy as input and returns answers drawn from one or more knowledge bases (KBs), which instantiate the input ontology with domain-specific information. AquaLog makes use of the GATE NLP platform, string metrics algorithms, WordNet and a novel ontology-based relation similarity service to make sense of user queries with respect to the target knowledge base. Finally, although AquaLog has primarily been designed for use with semantic web languages, it makes use of a generic plug-in mechanism, which means it can be easily interfaced to different ontology servers and knowledge representation platforms.
To appear in Proceedings of 9th international conference on applications of natural language to information systems, Manchester, 2004