BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Networks in Natural Language Processing - Stephen Clark and Sandro
  Bauer (University of Cambridge)
DTSTART:20110602T150000Z
DTEND:20110602T160000Z
UID:TALK30476@talks.cam.ac.uk
CONTACT:Eiko Yoneki
DESCRIPTION:In this talk we will describe two areas of Natural Language Pr
 ocessing (NLP) which may be of interest to the Networks research group. Fi
 rst\, Stephen will describe some recent work (of Brian Harrington) which a
 ttempts to build very large semantic networks automatically from large bod
 ies of text. These networks are intended to be general meaning representat
 ions which can potentially be used for a variety of NLP tasks and applicat
 ions\; in particular we will focus on the task of determining whether two 
 words or concepts in the network are semantically related.\n\nSecond\, San
 dro will describe his ongoing MPhil research work (a collaboration between
  the Networks and NLIP groups) which applies topic modelling techniques fr
 om NLP to a large collection of Tweets from a social networking tool\, whi
 ch also have geographical information encoded as meta-data. Some interesti
 ng patterns are observed with respect to how the conversations Twitter tha
 t users have vary according to geographical location.\n
LOCATION:FW26\, Computer Laboratory\, William Gates Builiding
END:VEVENT
END:VCALENDAR