It has been recognised that there are complex interdependencies between performance of a search technique and the s alient properties of the document collection on which it is deployed. Collection properties vary significantly across domains (e.g., legal vs patent vs biomedical documents). Therefore, the findings about a search technique on one collection cannot be automatically generalised to other collections. Practically, the search solutions should be tailored to the underlying document collection profiles, instead of simply adopting off-the-shelf Web search engine for everything. However, it is currently not well understood what collection properties are and how they are connected to the technique performance. This project aims to address this fundamental gap by developing, implementing and evaluating a comprehensive document collection profiling infrastructure to characterise document collections in relation to performance of various typical search techniques. The project will be in collaboration with Information Retrieval Facility (Vienna), the Open University and University of Essex.
Contact: Professor Dawei Song: + 44 (0)1224 262475; d.song at rgu.ac.uk
Applications should include a completed application form (available from http://www.rgu.ac.uk/researchdegrees/applicants/page.cfm?pge=26828), a detailed CV, two academic references, plus other required documents, and be emailed to researchdegrees at rgu.ac.uk or posted to the Research Degrees Office, the Robert Gordon University, Schoolhill, Aberdeen AB10 1FR, quoting reference IDEAS.
Closing date: 23rd April 2010