Incremental Query Generation

Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics, pages 183–191, Gothenburg, Sweden, April 26-30 2014. c⃝2014 Association for Computational Linguistics Incremental Query Generation Laura Perez-Beltrachini Faculty of Computer Science Free University of Bozen-Bolzano Bozen-Bolzano, Italy laura.perez@loria.fr Claire Gardent CNRS/LORIA Nancy, France claire.gardent@loria.fr Enrico Franconi Faculty of Computer Science Free University of Bozen-Bolzano Bozen-Bolzano, Italy franconi@inf.unibz.it Abstract We present a natural language genera- tion system which supports the incremen- tal specification of ontology-based queries in natural language. Our contribution is two fold. First, we introduce a chart based surface realisation algorithm which supports the kind of incremental process- ing required by ontology-based querying. Crucially, this algorithm avoids confusing the end user by preserving a consistent ordering of the query elements through- out the incremental query formulation pro- cess. Second, we show that grammar based surface realisation better supports the generation of fluent, natural sounding queries than previous template-based ap- proaches. 1 Introduction Previous research has shown that formal ontolo- gies could be used as a means not only to provide a uniform and flexible approach to integrating and describing heterogeneous data sources, but also to support the final user in querying them, thus im- proving the usability of the integrated system. To support the wide access to these data sources, it is crucial to develop efficient and user-friendly ways to query them (Wache et al., 2001). In this paper, we present a Natural Language (NL) interface of an ontology-based query tool, called Quelo1, which allows the end user to for- mulate a query without any knowledge either of the formal languages used to specify ontologies, or of the content of the ontology being used. Follow- ing the conceptual authoring approach described in (Tennant et al., 1983; Hallett et al., 2007), this interface masks the composition of a formal query 1krdbapp.inf.unibz.it:8080/quelo as the composition of an English text describ- ing the equivalent information needs using natu- ral language generation techniques. The natural language generation system that we propose for Quelo’s NL interface departs from similar work (Hallett et al., 2007; Franconi et al., 2010a; Fran- coni et al., 2011b; Franconi et al., 2010b; Franconi et al., 2011a) in that it makes use of standard gram- mar based surface realisation techniques. Our con- tribution is two fold. First, we introduce a chart based surface realisation algorithm which supports the kind of incremental processing required by on- tology driven query formulation. Crucially, this algorithm avoids confusing the end user by pre- serving a consistent ordering of the query ele- ments throughout the incremental query formu- lation process. Second, we show that grammar based surface realisation better supports the gener- ation of fluent, natural sounding queries than pre- vious template-based approaches. The paper is structured as follows. Section 2 discusses related work and situates our approach. Section 3 describes the task being addressed namely, ontology driven query formulation. It in- troduces the input being handled, the constraints under which generation operates and the opera- tions the user may …

Content truncated to 500 words