The AQUA Question-Answering System: Bi-Directional Dynamic Semantic Alignment in a Multiple-Ontology Environment

摘要

The AQUA Question Answering System uses two separate ontologically based systems in its operation. The first system, a knowledge-based information extraction system, derives the content from text documents (and queries) and converts them into an internal text meaning representation form (TMR). The second ontologically based system is the answer formulation unit, which maintains a separate ontology in a different form from the first. Answers produced by the answer formulation system are in Knowledge Interchange Format (KIF). These answers must be converted back into the text meaning representation where they can be translated by an answer generation unit into natural language responses to the user query. The key technical challenge of this system is bi-directionally translating between the two ontologies when each is dynamically changing in the course of operations. This paper presents a description of our technical solution to this challenging problem. Furthermore, the approach we have taken is one that can be extended to other ontologically based systems, or to systems with more than two ontologies. It is generic in its approach, in that the specific ontologies involved in the solution do not determine the nature of the semantic alignment process.