BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Linguists-defined and Machine-induced Natural Language Structures 
 to Executable Logical Forms - Siva Reddy (Stanford University)
DTSTART:20170615T100000Z
DTEND:20170615T110000Z
UID:TALK72597@talks.cam.ac.uk
CONTACT:Mohammad Taher Pilehvar
DESCRIPTION:Querying a database to retrieve an answer\, telling a robot to
  perform an action\, or teaching a computer to play a game are tasks requi
 ring communication with machines in a language interpretable by them. Here
  we consider the task of converting human language to a knowledge-base (KB
 ) language for question-answering. While human languages are sequential in
  nature with latent structures\, machine interpretable languages have expl
 icit formal structures. The computational linguistics community has create
 d several treebanks to understand the formal structures of human languages
 \, e.g.\, universal dependencies. But are these helpful in deriving target
  language structures?\n\nIn the first part of the talk\, I will discuss ho
 w to convert universal dependencies in multiple languages to both general-
 purpose and kb-executable logical forms. In the second part\, I will prese
 nt a neural model on how to induce task-specific natural language structur
 es. I will discuss the similarities and differences between linguists-defi
 ned and machine-induced structures. 
LOCATION: SR-24\, English Faculty Building\, 9 West Road (Sidgwick Site)
END:VEVENT
END:VCALENDAR