Description
PowerAqua is a multi-ontology-based Question Answering (QA) system, which takes as input queries expressed in natural language and is able to return answers drawn from relevant distributed resources on the Semantic Web. In contrast with any other existing natural language front end, PowerAqua is not restricted to a single ontology and therefore provides the first comprehensive attempt at supporting open domain QA on the Semantic Web.

PowerAqua evolved from the earlier AquaLog system, our portable ontology-based semantic QA for intranets. PowerAqua extends the capabilities provided by AquaLog to support QA in the open domain of the Semantic Web . PowerAqua is designed to take advantage of the vast amount of heterogeneous semantic data offered by the SW in order to interpret a query, without making any assumptions of the relevant ontologies to a particular query a priori.

The key challenges in order to be able to answer queries in the open SW scenario by dynamically locating and combining information from multiple domains are:
  • Locating the ontologies relevant to a query (which footballer's wife is a fashion celebrity?")
  • Identifying semantically sound mappings ("capital" given by its ancestor "city")
  • Providing complete coverage of a user's query (often by combining information from multiple ontologies)

We envision an scenario where the user has to interact with thousand of ontologies structured according to hundred of ontologies. PowerMap is the solution adopted by PowerAqua to map user terminology into ontology compliant terminology, distributed across ontologies, in real time. See the approach and component section and related publications for an overview of the algorithm.

To conclude with, PowerAqua balances the heterogeneous and large scale semantic data with giving results in real time across ontologies, to translate user terminology into distributed semantically sound terminology, so that the concepts which are shared by assertions taken from different ontologies have the same sense. The goal is to handle queries which require to be answered not only by consulting a single knowledge source but combining multiple sources, and even domains.



AKT