BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Understanding decisions\, relationships and behaviors through text
 … and Natural Language Processing
DTSTART:20180911T101500
DTEND:20180911T113000
DTSTAMP:20260407T034448Z
UID:615bb23b6123befc0bfa57316991f231b446b86b8a763cb6724a0bd2
CATEGORIES:Conferences - Seminars
DESCRIPTION:Léa Deleris\nAbstract:\nHave you ever been stuck in meetings 
 with discussions going in circles\, meetings from which no decision emerge
 s or one with which everyone is frustrated? \nDo you sometimes feel that 
 you misunderstood the relationships among members of your professional or 
 personal circles?\nHave you ever wondered how you could get to stop smokin
 g\, eat healthy and start exercising?\nIf you answered yes to any of those
  questions\, come to this talk where I will present three projects that ai
 m at understanding decisions\, relationships and behaviors (respectively) 
 drawing from text sources.\nIn the DECODE project (Decision Conversations 
 Decoded and Explained)\, we analyze transcripts of discussions\, typically
  meetings\, in which a decision is being discussed. Our goal is simple: fo
 llow the decision process\, automatically keep track of the options that a
 re being considered and why they are being proposed and summarize the info
 rmation in an actionable form.\nIn the Relationship Insights project\, we 
 seek to decipher how we relate to one another. Making use of case notes\, 
 speech transcripts\, posts\, books etc. as the source of information about
  interactions\, we extract qualitative and quantitative information about 
 interactions among persons that extends beyond building a social network. 
 Such information is relevant for instance in social care\, sales and intel
 ligence work.\nIn the Human Behaviour-Change Project (HBCP)\, a collaborat
 ion between University College London\, Cambridge University\, University 
 of Aberdeen and IBM Research\, we are developing a knowledge system that a
 utomatically extracts and reasons with findings from behavior change inter
 ventions studies\, starting with smoking cessation interventions. Our ambi
 tion is to create a system that can help researcher and policy makers bett
 er understand what works and in which context?\n \nBio:\nLéa received M.
 S. degrees in Economic Systems from Ecole Polytechnique (France) in 1999 a
 nd in Management Science and Engineering from Stanford University in 2001.
  She joined IBM Research in 2006 just after graduating from Stanford Unive
 rsity with a PhD. in Management Science and Engineering.\nShe has been a R
 esearch Staff Member and Manager in IBM Ireland since April 2010. One of h
 er previous roles was to lead the Risk Management Collaboratory project (s
 ee Projects). Before moving to Ireland\, she was a member of the Risk Anal
 ytics group of the Business Application and Mathematical Science Departmen
 t at the IBM TJ Watson Research Center.\nLéa currently manages a team of 
 10+ researchers and software engineers working on a diversity of projects 
 that seek to make use of artificial intelligence and natural language proc
 essing to support decision making in a variety of situations including soc
 ial care\, health care\, chemistry but also sales management.\nHer persona
 l research interests lies in decision theory and risk analysis on one side
  and artificial intelligence (and in particular natural language processin
 g) on the other side. Currently\, her work presents a mixture of applied a
 nd conceptual work\, including (i) information extraction in the field of 
 behavior change (ii) causal modeling for recommendation of interventions i
 n smoking cessation\, (iii) learning algorithms for Bayesian networks from
  messy data and (iv) targeted sentiment analysis.\n \n\n \n \nHost: Swi
 ss Data Science Center\, Olivier Verscheure\n 
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR