Probabilistic Topic Modeling In Web Search

PhD Thesis Proposal Defence


Title: "Probabilistic Topic Modeling In Web Search"

by

Mr. Di JIANG


Abstract:

In recent years, probabilistic topic modeling is gaining significant 
momentum in research fields such as artificial intelligence and machine 
learning. Although many probabilistic topic models have been intensively 
studied in these two research fields and demonstrated promising 
performance in several applications, applying them in web search scenarios 
has rarely been explored in existing work.

In this thesis, we demonstrate the effectiveness of probabilistic topic 
modeling in enhancing a variety of web search applications. Our study 
covers three major functionalities of contemporary search engines:

1) Web Search Query Log Analytics;
2) Web Search Query Suggestion;
3) Web Search Query Processing.

We validate our methods through extensive experiments and discuss several 
interesting research directions of probabilistic topic modeling in web 
search scenario.


Date:			Tuesday, 29 April 2014

Time:                   3:30pm - 5:30pm

Venue:                  Room 5504
                         lifts 25/26

Committee Members:	Dr. Wilfred Ng (Supervisor)
 			Dr. Ke Yi (Chairperson)
 			Prof. Dik-Lun Lee
 			Dr. Raymond Wong


**** ALL are Welcome ****