Semantic Query Auto-Completion for the Retrieval of Research Artifacts
Shwetaben Ramanikbhai Khatra
Query Auto Completion (QAC) is a fundamental element of information retrieval. QAC provides assistance to users in query formulation by displaying suggestions for query completion. Conventional QAC approaches are either based on rule-based, heuristic or learning-based approaches. In addition, approaches already exist that use graph-based methods to evaluate semantic relationships among search terms. Semantic Web technologies, however, seem not to have been considered so far.
For repositories that contain research data or research publications, detailed metadata descriptions generally exist that contain administrative metadata about authors or creators, associated research areas or keywords, as well as content-related descriptive metadata. Furthermore, relationships exist between data and their authors or creators, as well as between individual data. The totality of this information forms a semantic network, which can be mapped into a knowledge base. On this basis, there are various metrics that could be incorporated into the process of ranking candidates for query completion.
The goal of this work is to develop a semantic approach to query auto completion, or to extend a conventional approach with semantic metrics. To this end, a requirements analysis must first be carried out and the state of the art must be investigated. Existing solutions are to be classified and evaluated according to the requirements. Subsequently, a QAC approach using semantic methods has to be designed and described. The designed approach has to be demonstrated in a prototypical implementation. In addition, the practicability and acceptance of the approach must be assessed in a suitable evaluation.