AQUA: A Question Answering System for Heterogeneous Sources

This paper describes AQUA our question answering over the Web. AQUA was designed to work over heterogeneous sources. This means that AQUA is equipped to work as closed domain and in addition to open-domain question answering. As a first instance, AQUA tries to answer a question using a Knowledge base. If a query cannot be satisfied over a knowledge base/database. Then, AQUA tries to find an answer on web pages (i.e. it uses as corpus the internet as resource). Our system uses NLP (Natural Language Processing), First order logic and Information Extraction technologies. AQUA has been tested using an ontology which describes academic life.

Keywords Ontologies, Information Extraction, Machine Learning