BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Joint A* Syntactic and Semantic Parsing for CCG - Mike Lewis\, Uni
 versity of Washington
DTSTART:20150925T110000Z
DTEND:20150925T120000Z
UID:TALK61140@talks.cam.ac.uk
CONTACT:Tamara Polajnar
DESCRIPTION:Joint models of syntactic and semantic parsing have the potent
 ial to improve performance on both tasks—but to date\, the best results 
 have been achieved with pipelines. I will introduce a new joint model usin
 g CCG\, which is motivated by the close link between CCG syntax and semant
 ics. Semantic roles are recovered by labelling the deep dependency structu
 res produced by the grammar. Furthermore\, I will show how to exploit CCG'
 s strong lexicalization to introduce a new A∗ parsing algorithm---which 
 finds optimal parses over 5 times faster than CKY parsing. Our joint model
  is the first to substantially improve both syntactic and semantic accurac
 y over a comparable pipeline\, and also achieves state-of-the-art results 
 for a non-ensemble semantic role labelling model. 
LOCATION:FW26\, Computer Laboratory
END:VEVENT
END:VCALENDAR