[Colloq] Fwd: Thesis Defense: Evangelos Kanoulas, August 29th

[Diane Keys]

Diane Keys 
Grants Coordinator 
College of Computer & Information Science 
202 West Village H 
617-373-2461 
fax: 617-373-5121 

----- Forwarded Message ----- 
From: "Alexa Del Greco" <alexa at ccs.neu.edu> 
To: faculty at ccs.neu.edu, "diane" <diane at ccs.neu.edu>, "Rachel Kalweit" <rachelb at ccs.neu.edu>, "lackaye" <lackaye at ccs.neu.edu>, "dhodgkin" <dhodgkin at ccs.neu.edu>, "je" <je.wong at neu.edu>, "tricia" <tricia at ccs.neu.edu>, "krissy" <krissy at ccs.neu.edu> 
Sent: Thursday, August 28, 2008 1:08:40 PM GMT -05:00 US/Canada Eastern 
Subject: Fwd: Thesis Defense: Evangelos Kanoulas, August 29th 

Evangelos Kanoulas will be doing his Thesis Defense.  Information follows. 

Thesis Proposal : Building reliable test and learning collections in IR 

Proposal Date and Time : Friday, August 29th, 3:45pm, 366WVH 

Abstract : 
Research in Information Retrieval has significantly benefited from the availability of standard test collections and the use of these collections for comparative evaluation of the effectiveness of different retrieval system configurations in controlled laboratory experiments. In an attempt to design large and reliable test collections decisions regarding the assembly of the document corpus, the selection of topics, the formation of relevance judgments and the development of evaluation measures are particularly critical. 

Furthermore, recently, building retrieval systems has been viewed as a machine learning task resulting in the development of a learning-to-rank methodology widely adopted by the community. It is apparent that the design and construction methodology of learning collections, along with the selection of the evaluation measure to be optimized for significantly affects the quality of the resulting retrieval system. 

We propose (a) to study the design and construction methodology of test and learning collections and (b) to compare and develop evaluation measures that can be reliably used for comparative evaluations among retrieval systems and learning-to-rank tasks. 


Committee Members [justification]: 
Javed Aslam 
James Allan [cv] 
Rajmohan Rajaraman 
Betty Salzberg