BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Efficient Constrained Inference and Structured Neural Networks for
  Semantic Role Labeling - Oscar Täckström\, Google
DTSTART:20151204T120000Z
DTEND:20151204T130000Z
UID:TALK62579@talks.cam.ac.uk
CONTACT:Kris Cao
DESCRIPTION:*Abstract:*\n\nI will describe some of our recent advances in 
 the prediction of predicate-argument structure in natural language text.\n
 \nFirst\, I will describe a dynamic programming algorithm for efficient co
 nstrained inference in semantic role labeling. The algorithm efficiently c
 aptures a majority of the structural constraints examined by prior work in
  this area\, which has resorted to either approximate methods or slow inte
 ger linear programming solvers. In addition\, it allows for structured lea
 rning\, with respect to constrained conditional likelihood\, which leads t
 o improved predictions over a locally learned model.\n\nSecond\, I will de
 scribe how the potential functions in the graphical model corresponding to
  the dynamic program can be replaced with neural networks. In addition to 
 increased modeling power and automatically induced feature combinations\, 
 this allows us to embed phrasal arguments and semantic roles jointly in th
 e same vector space\, and provides a flexible framework for multi-task lea
 rning by the embedding of semantic roles from multiple annotation schemes 
 in a shared vector space.\n\nWith these advances\, both by themselves and 
 combined\, we obtain state-of-the-art results on both PropBank- and FrameN
 et-annotated datasets.\n\n*Short bio:*\n\nOscar Täckström is a research 
 scientist at Google in New York\, where he works primarily on the semantic
  analysis of text and question answering from structured knowledge bases. 
 Before joining Google in 2013\, he was a PhD student in the Computational 
 Linguistics group at Uppsala University and a research scientist at the Sw
 edish Institute of Computer Science. In his thesis\, he explored the use o
 f incomplete and cross-lingual supervision for learning statistical models
  in natural language processing. Together with Ryan McDonald and Jakob Usz
 koreit\, he received the IBM Best Student Paper Award at NAACL 2012.
LOCATION:FW26\, Computer Laboratory
END:VEVENT
END:VCALENDAR