BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Unsupervised Modeling  of Twitter Conversations - Diarmuid Ó Séa
 ghdha (University of Cambridge)
DTSTART:20101115T123000Z
DTEND:20101115T133000Z
UID:TALK27996@talks.cam.ac.uk
CONTACT:Marek Rei
DESCRIPTION:At next weeks reading group Diarmuid will present the followin
 g paper:\n\nAlan Ritter\, Colin Cherry and Bill Dolan. 2010. Unsupervised 
 Modeling of Twitter Conversations. In Proceedings of NAACL-10.\n\nhttp://a
 clweb.org/anthology-new/N/N10/N10-1020.pdf\n\nAbstract: We propose the fir
 st unsupervised approach to the problem of modelling dialogue acts in an o
 pen domain. Trained on a corpus of noisy Twitter conversations\, our metho
 d discovers dialogue acts by \n> clustering raw utterances. Because it acc
 ounts for the sequential behaviour of these acts\, the learned model can p
 rovide insight into the shape of communication in a new medium. We address
  the challenge of evaluating the emergent model with a qualitative visuali
 zation and an intrinsic conversation ordering task. This work is inspired 
 by a corpus of 1.3 million Twitter conversations\, which will be made publ
 icly available.\n\nThis huge amount of data\, available only because Twitt
 er blurs the line between chatting and publishing\, highlights the need to
  be able to adapt quickly to a new medium.\n\nMonday 15th\, 12:30 in GS15.
 \n\nMarek\n
LOCATION:GS15\, Computer Laboratory
END:VEVENT
END:VCALENDAR