BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Learning-to-Rank for Information Retrieval  - He Yu He\, Murray Ed
 wards College
DTSTART:20210217T190000Z
DTEND:20210217T193000Z
UID:TALK157597@talks.cam.ac.uk
CONTACT:Matthew Ireland
DESCRIPTION:In a world flooded with information\, it is becoming increasin
 gly challenging to extract desired information from a large pool of data. 
 Learning-to-Rank (LTR) uses machine learning technologies to solve the pro
 blem of information retrieval. One typical usage of LTR is in the ranker o
 f a search engine\, which matches processed queries with indexed documents
 .\n\nIn this talk\, I will provide an overview of Learning-to-Rank framewo
 rk\, and explain the 3 major approaches: Pointwise\, Pairwise\, and Listwi
 se\; and compare their limitations. I will also elaborate on each approach
  with an example algorithm developed upon the idea of AdaBoost. 
LOCATION:Online\, via MS Teams
END:VEVENT
END:VCALENDAR