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 information. The availability of semantic markup on the web also opens the way to novel, sophisticated forms of question answering. While semantic information can be used in several different ways to improve question answering, an important (and fairly obvious) consequence of the availability of semantic markup on the web is that this can indeed be queried directly. Hence, in the first instance, the work on the AquaLog query answering system is based on the premise that the semantic web will benefit from the availability of natural language query interfaces, which allow users to query semantic markup viewed as a knowledge base. Moreover, interestingly from a research point of view, it provides a new ‘twist’ on the old issues associated with NLDB research. It is our view that the semantic web provides a new and potentially very important context in which results from this area of research can be applied.

AquaLog is a portable question-answering system which takes queries expressed in natural language and an ontology as input and returns answers drawn from one or more knowledge bases (KBs), which instantiate the input ontology with domain-specific information. We say that AquaLog is portable, because its architecture is completely independent from specific ontologies and knowledge representation systems. Given a knowledge representation system, AquaLog can be configured for a particular ontology in a matter of minutes. AquaLog is also portable with respect to knowledge representation, because it uses a modular architecture based on a plug-in mechanism to access information about an ontology, using an OKBC-like protocol.

AquaLog present an elegant solution in which different strategies are combined together. It makes use of the GATE NLP platform as part of the linguistic process , string metrics algorithms , a learning mechanism as a solution to manage lexical resources, including domain-dependent lexica and generic resources such as WordNet AquaLog also makes use of a novel ontology-based relation similarity service to make sense of user queries with respect to the target knowledge base.

We are currently working on a new system, which is called PowerAqua, which extends AquaLog by sourcing answers to natural language queries by accessing any semantic document available on the Semantic Web.

Try the AquaLog demo!