Dissertation project abstract:

Natural Language Generation Applied to
Intelligent Query Interfaces
(PhD-Thesis Proposal)
Paolo Dongilli

The present research aims at building a bridge between Intelligent Query Interfaces
and Natural Language Generation technologies. The idea is to have
a query interface enabling the users to access heterogeneous data sources by
means of an integrated ontology. The query interface supports the users in
formulating a precise conjunctive query where the intelligence of the interface
is driven by an ontology describing the domain of the data in the information
system. The main challenge is that the underlying conjunctive query must be
presented to the user in natural language and the stepwise refinements of the
query made by the user are refinements that maintain the grammaticality of
the sentences representing the query. This can be considered a step towards a
question answering system where the question is not freely inserted by the user,
but instead the user is guided in building it according to the knowledge domain
chosen.