BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Read Less\, Learn More: Extracting Key News Themes - Joshua Bambri
 ck\, Bloomberg
DTSTART:20191022T121500Z
DTEND:20191022T133000Z
UID:TALK133633@talks.cam.ac.uk
CONTACT:Christine Georgiou
DESCRIPTION:With 2\,000\,000 stories being ingested by Bloomberg each day\
 , our customers have an information overload problem. How can you find and
  consume all the news events relevant to a topic you are interested in\, w
 ithout trawling through redundant articles from many different agencies?\n
 News Themes is a solution released earlier this year! In this talk\, I’l
 l take you on a whirlwind tour of what a ‘news theme’ is and how we ap
 ply recent NLP research in clustering & summarisation to make them work.\n
LOCATION:FW26\, Computer Laboratory
END:VEVENT
END:VCALENDAR