BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Learning region based representations of categories - Steven Schoc
 kaert\, Cardiff University
DTSTART:20191031T110000Z
DTEND:20191031T120000Z
UID:TALK134032@talks.cam.ac.uk
CONTACT:Edoardo Maria Ponti
DESCRIPTION:The use of vectors for representing the entities from a given 
 knowledge base is now standard practice in Natural Language Processing. Fr
 om a knowledge representation point of view\, however\, it seems more intu
 itive to model categories as regions (or distributions) rather than single
  vectors. A given individual is then assumed to belong to some category if
  the vector representation of that individual belongs to the corresponding
  region. Apart from increasing the interpretability of vector space repres
 entations\, such region based representations also significantly expand th
 e range of knowledge that can be expressed. In particular\, we can show th
 at region based vector space representations are able to capture a large s
 ub-fragment of the class of existential rules. Unfortunately\, estimating 
 meaningful region representations in high-dimensional vector spaces is cha
 llenging\, especially because they often have to be estimated from a very 
 small number of examples. In our recent work\, we have proposed a number o
 f solutions that try to alleviate the lack of sufficient training examples
  by exploiting prior knowledge about the semantic relationships between di
 fferent categories.
LOCATION:Board room\, Faculty of English\, 9 West Rd (Sidgwick Site)
END:VEVENT
END:VCALENDAR