BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Incremental CCG parsing and its applications - Bharat Ram Ambati\,
  University of Edinburgh/Apple
DTSTART:20160527T110000Z
DTEND:20160527T120000Z
UID:TALK65992@talks.cam.ac.uk
CONTACT:Kris Cao
DESCRIPTION:In this talk\, we first present an incremental algorithm for t
 ransition-based CCG parsing. As previously available shift-reduce CCG pars
 ers use CCGbank derivations which are mostly right branching and non-incre
 mental\, we design our algorithm based on the dependencies resolved rather
  than the derivation. Our novel algorithm builds a dependency graph in par
 allel to the CCG derivation which is used for revealing the unbuilt struct
 ure without backtracking. \n\nWe then show the usefulness of an incrementa
 l CCG parser for predicting relative sentence complexity. Given a pair of 
 sentences from wikipedia and simple wikipedia\, we build a classifier whic
 h predicts if one sentence is simpler/complex than the other. We show that
  features from a CCG parser in general and incremental CCG parser in parti
 cular are more useful than a chart-based phrase structure parser both in t
 erms of speed and accuracy.
LOCATION:FW26\, Computer Laboratory
END:VEVENT
END:VCALENDAR