Shallow language processing, deep language processing and domain ontologies

A new line of our research concerns the combination of shallow processing, deep processing and domain ontologies for question answering. In our QA system QUETAL, we combine question answering on the basis of structured data with open domain IR supported question answering as it can be employed for questioning the Web. The new approach exploits RMRS as the formalism for translating natural language questions into SQL queries. Ontologies are utilized for structuring the data, constructing the appropriate semantics for the QA systems and for the interpretation of the questions. We demonstrate the interaction of shallow and deep technologies in the QA system and stress the knowledge related aspects. We finally discuss the advantages and open problems connected with our approach. In a brief outlook we programmatically sketch the planned next steps in the DELPH-IN community towards bridging the gap between advanced semantic language processing and state-of-the-art knowledge technology.