DaNaLIX: a Domain-adaptive Natural Language Interface for Querying XML

摘要

We present DaNaLIX, a prototype domain-adaptive natural language interface for querying XML. Our system is an ex- tension of NaLIX, a generic natural language interface for querying XML [4, 5]. While retaining the portability of a purely generic system like NaLIX, DaNaLIX can exploit do- main knowledge, whenever available, to its advantage for query translation. More importantly, in DaNaLIX such do- main knowledge does not have to be pre-defined; instead it can be automatically obtained from the interactions between a user and the system. In this demonstration, we describe the overall architecture of DaNaLIX. We also demonstrate how a generic system like DaNaLIX can take advantage of domain knowledge to improve its usability and query trans- lation accuracy. In addition, we show DaNaLIX still possesses the portability of a generic system by using data collections from three different domains. Finally, we present how do- main knowledge can be obtained through user interactions in an automatic fashion.