NLPX at INEX 2004

Users of information retrieval (IR) systems require an interface that is\udpowerful and easy-to-use in order to fulfill their information requirement. In\udXML-IR systems this is a non-trivial task since users expect these systems to\udfulfill both their structural and content requirements. Most existing XML-IR\udsystems accept queries formatted in formal query languages, however, these\udlanguages are difficult to use. This paper presents NLPX – an XML-IR system\udwith a natural language interface that is user friendly enough so it can be used\udintuitively, but sophisticated enough to be able to handle complex structured\udqueries. NLPX accepts English queries that contain both users’ content and\udstructural requirements. It uses a set of grammar templates to derive the structural\udand content requirements and translates them into a formal language\ud(NEXI). The formal language queries can then be processed by many existing\udXML-IR systems. The system was developed for participation in the NLP\udTrack of the INEX 2004 Workshop, and results indicated that natural language\udinterfaces are able to capture users’ structural and content requirements, but not\udas accurately as some formal language interfaces