BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Representation Learning and Neuro-Symbolic Reasoning in Knowledge 
 Graphs and Natural Language - Pasquale Minervini\, University College Lond
 on
DTSTART:20181025T100000Z
DTEND:20181025T110000Z
UID:TALK113089@talks.cam.ac.uk
CONTACT:Edoardo Maria Ponti
DESCRIPTION:*Abstract*: Knowledge Graphs (KGs) are graph-structured Knowle
 dge Bases where facts are encoded by links between entities\, and their us
 e is pervasive both in industry (e.g. see Google Knowledge Graph\, Microso
 ft Satori) and academia (YAGO\, DBpedia\, NELL\, OpenCyc). KGs are extreme
 ly useful\, as they provide automated systems with machine-readable domain
  specific knowledge\, allowing AI systems to perform deductive (and induct
 ive) reasoning in a variety of domains. The talk will discuss about Repres
 entation Learning in KGs\, its shortcomings\, how we can introduce First-O
 rder Logic constraints in the learned representations\, and how we can ext
 end such techniques to NLP models. Then the speaker will talk about his re
 cent work in neuro-symbolic reasoning - namely on Neural Theorem Provers [
 1\, 2] - and how we can perform explainable deductive reasoning jointly on
  Knowledge Graphs and Natural Language at scale.\n\n[1] https://arxiv.org/
 abs/1705.11040\n\n[2] https://arxiv.org/abs/1807.08204\n\n*Bio*: Pasquale 
 Minervini is a Postdoctoral Research Associate in Statistical Natural Lang
 uage Processing\nand Machine Learning in the UCL Machine Reading group. He
  is funded by a Machine Reading grant from the Allen Institute\nfor Artifi
 cial Intelligence (AI2).
LOCATION:Boardroom\, Faculty of English\, West Road
END:VEVENT
END:VCALENDAR