Odysseus

CLARITY is carrying out research in conjunction with an Irish software company on a project involving search and recommendation techniques. The project is based around a platform which connects consumers to suppliers of services using a wide range of social network and web 2.0 technologies.

Providing search over service provider profiles is an integral part of the platform. However, finding optimal ways to improve searching capabilities is a large research challenge. Typically, little support is provided to searchers when their queries, which can be vague, poorly formed or too specific, fail to deliver appropriate results. This can leave searchers feeling frustrated and cause them to have to search again from scratch or give up completely.

In this project, the student will develop and test the automatic generation of hierarchical concept taxonomies which will be incorporated into the search technology. The student will concentrate on quality taxonomies which can help to fine tune relevant search results in order generalise unsuccessful/incomplete queries in order to reduce search fails.

The student will benefit from access to a number of CLARITY researchers who are working on related issues. CLARITY will also provide access to real-world data for testing and development. This project allows the student to work on research solutions which will be incorporated into an industry platform, giving the student a valuable and unique insight into aspects of both research and industry.

Workplan

Weeks 1-2: Background Research. The student will look into related research in the areas of semantic search and automatic taxonomy generation. The student will also get up-to-speed with other developments in this research-industry partnership.

Weeks 3-5: Automatic taxonomy generation. The student will implement various taxonomy generation strategies based on data freely available on the internet and data from the industry partner.

Weeks 6-8: Taxonomy Viewer/Manager Interface. The user will develop a tool for testing, managing and viewing results of their taxonomy generation strategies.

Weeks 9-10: Testing and fine tuning. The student will test their strategies across a wide range of data and fine tune the parameters of their generation techniques.

Supporting Material:

Heymann, Paul and Garcia-Molina, Hector (2006) "Collaborative Creation of Communal Hierarchical Taxonomies in Social Tagging Systems". Technical Report. Stanford.

Paul Buitelaar, Philipp Cimiano and Bernardo Magnini. "Ontology Learning from Text: An Overview".
In Paul Buitelaar, Philipp Cimiano and Bernardo Magnini (Eds.), Ontology Learning from Text: Methods, Applications and Evaluation, pp. 3-12, IOS Press, 2005.