BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Topic-Aware Convolutional Neural Networks for Extreme Summarizatio
 n - Shashi Narayan\, University of Edinburgh / Google
DTSTART:20190201T120000Z
DTEND:20190201T130000Z
UID:TALK117862@talks.cam.ac.uk
CONTACT:Andrew Caines
DESCRIPTION:We introduce extreme summarization\, a new single-document sum
 marization task which does not favor extractive strategies and calls for a
 n abstractive modeling approach. The idea is to create a short\, one-sente
 nce news summary answering the question “What is the article about?”. 
 We have collected a real-world\, large-scale dataset for this task by harv
 esting online articles from the British Broadcasting Corporation (BBC). We
  propose a novel abstractive model which is conditioned on the article’s
  topics and based entirely on convolutional neural networks. We demonstrat
 e experimentally that this architecture captures long-range dependencies i
 n a document and recognizes pertinent content\, outperforming an oracle ex
 tractive system and state-of-the-art abstractive approaches when evaluated
  automatically and by humans. \n\n*Bio:* Shashi Narayan is a research asso
 ciate at the School of Informatics at the University of Edinburgh. He will
  join Google London in February.  His research focuses on natural language
  generation\, understanding and structure predictions. A major aim of his 
 research is to build on the hypothesis that tailoring a model with knowled
 ge of the task structure and linguistic requirements\, such as syntax and 
 semantics\, leads to a better performance. His research has appeared in co
 mputational linguistics journals (e.g.\, TACL and Computational Linguistic
 s) and in conferences (e.g.\, ACL\, EMNLP\, NAACL\, COLING\, EACL and INLG
 ). He was nominated on the SIGGEN board (2012-14) as a student member. He 
 served as an area co-chair for Generation and gave a tutorial on "Deep lea
 rning approaches to text production" at NAACL HLT 2018. He is currently wr
 iting a book on the same topic. He will serve as an area co-chair for Summ
 arization at ACL 2019. 
LOCATION:FW26\, Computer Laboratory
END:VEVENT
END:VCALENDAR
