BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Labelling Topics Using Neural Networks - Nikolaos Aletras\, Amazon
  Research Cambridge
DTSTART:20171110T120000Z
DTEND:20171110T130000Z
UID:TALK95071@talks.cam.ac.uk
CONTACT:Anita Verő
DESCRIPTION:Much of the information in large digital libraries is often st
 ored in an unstructured way and is not organised using any automated syste
 m. That is usually overwhelming for users in a way that makes it difficult
  to find specific information or explore such data collections. A particul
 ar set of unsupervised statistical methods\, namely topic models have been
  extensively used in Natural Language Processing and Information Retrieval
  for automatically analysing and organising document collections. Topics g
 enerated by topic models are typically presented as a list of terms. Autom
 atic topic labelling is the task of generating a succinct label that summa
 rises the theme or subject of a topic\, with the intention of reducing the
  cognitive load of end-users when interpreting these topics. In this talk\
 , I will present neural network approaches to labelling topics with text a
 nd images showcasing their effectiveness on providing meaningful represent
 ations of the topics.\n\nBio:\nI am an Applied Scientist at Amazon Researc
 h Cambridge. Prior to that\, I worked as a Research Associate at the Depar
 tment of Computer Science at UCL and I completed a PhD in NLP at the Depar
 tment of Computer Science at the University of Sheffield. My main research
  interests are in Natural Language Processing and Machine Learning. More s
 pecifically\, I'm interested in applying statistical methods for detecting
  and interpreting the underlying topics in large volumes of text data. I a
 lso develop methods to analyse text and uncover patterns in data to solve 
 problems in other scientific areas such as social and legal science.
LOCATION:FW26\, Computer Laboratory
END:VEVENT
END:VCALENDAR