BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Learning with Explanations - Tim Rocktäschel\, Facebook AI Resear
 ch
DTSTART:20181115T110000Z
DTEND:20181115T120000Z
UID:TALK114871@talks.cam.ac.uk
CONTACT:Edoardo Maria Ponti
DESCRIPTION:Abstract: Despite the success of deep learning models in a wid
 e range of applications\, these methods suffer from low sample efficiency 
 and opaqueness. Low sample  efficiency limits the application of deep lear
 ning to domains for which abundant training data exists whereas\nopaquenes
 s prevents us from understanding how a model derived a particular output\,
  let alone how to correct systematic errors\, how to remove bias\, or how 
 to incorporate common sense and domain knowledge. To address these issues 
 for knowledge base completion\, we developed end-to-end differentiable pro
 vers which (i) learn neural representations of symbols in a knowledge base
 \, (ii) make use of similarities between learned symbol representations to
  prove queries to the knowledge base\, (iii) induce logical rules\, and (i
 v) use provided and induced rules for multi-hop reasoning. I will present 
 our recent efforts in applying differentiable provers to statements in nat
 ural language texts and large-scale knowledge bases. Furthermore\, I will 
 introduce two datasets for advancing the development of models capable of 
 incorporating natural language explanations: eSNLI\, crowdsourced explanat
 ions for over half a million sentence pairs in the Stanford Natural Langua
 ge Inference corpus\, and ShARC\, a conversational question answering data
 set with natural language rules.
LOCATION:Boardroom\, Faculty of English\, West Road
END:VEVENT
END:VCALENDAR