Samir Tartir, Bobby McKnight, and I. Budak Arpinar.
Abstract
As more data is being semantically annotated, it is getting more common that researchers in multiple disciplines rely on repositories that contain large amounts of semantic data in the form of ontologies. One of the main issues currently facing these researchers is the lack of easy-to-use interfaces for data retrieval, due to the need to use special query languages or applications. In addition, the knowledge in these repositories might not be up-to-date due to missing some existing knowledge when the data was created, or due to the discovery of new knowledge after the repositories was created. In this paper, we propose a new approach that allows users to query semantic data repositories using natural language questions. If some parts of the questions cannot be answered due to lack of knowledge, our approach attempts to answer these parts from web documents and use these answers.
سمير الترتير | Samir Tartir | 4445