University of Cambridge > > NLIP Seminar Series > Constructing topical hierarchies for Expertise Mining

Constructing topical hierarchies for Expertise Mining

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Tamara Polajnar.

In this age of pervasive internet access we have become accustomed to rely on web search for our most basic information needs. But complex queries in knowledge-intensive organisations, as well as in the academic environment, are best answered by direct interaction with domain experts. Current approaches for expert finding are based on keyphrase search, relying on exact string matches to identify experts. What is needed is support for exploratory search and discovery of expertise topics and experts, as well as content-based measures of expertise. Hierarchical structures have long been considered for content organisation and navigational support, but in this talk we hypothesize that they also provide useful information for measuring expertise.

Building upon research for term extraction and taxonomy construction, we propose an Expertise Mining approach to expertise topic extraction, expert finding and expert profiling. In particular, we discuss a term extraction approach that considers the level of specificity of a term within a domain, a graph-based algorithm for topical hierarchy construction using a global generality measure, and a novel measure of expertise based on topical hierarchies.

This work has been part of the Saffron project [1], a system that provides insight into several Computer Science domains and which was deployed at different conferences as a tool for finding collaborators.


This talk is part of the NLIP Seminar Series series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


© 2006-2021, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity