BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Principled Approaches to Automatic Text Summarization
DTSTART:20181114T090000
DTEND:20181114T103000
DTSTAMP:20260408T035040Z
UID:dde7184dffb80af8e51eb6dba7dd1a3e78cafaccb78520a1e81546bb
CATEGORIES:Conferences - Seminars
DESCRIPTION:Maxime Peyrard\nIn this talk\, we will discuss approaches to t
 ackle  Automatic Text Summarization. We'll concentrate on content selecti
 on\, the inherent problem of summarization which is controlled by the noti
 on of information Importance. To this end\, we'll introduce a simple and i
 ntuitive formulation of summarization as two components: a summary scoring
  function indicating how good is a text as a summary of the given sources\
 , and an optimization technique extracting a high-scoring summary. We will
  briefly discuss how one can empirically "learn" the summary scoring funct
 ion from data yielding new summarization systems and new evaluation metric
 s. Then\, alternatively\, we will take a more theoretical strategy and for
 malize the vague notion of Importance. Intuitively\, Importance can be see
 n as the measure that guides which choices to make when information must b
 e discarded.\n\nMaxime Peyrard is a Ph.D. student at the University of Dar
 mstadt\, working on machine learning and natural language processing.\nHis
  research has focused on unifying existing summarization approaches into a
  generic optimization problem. He was also interested in ways to leverage 
 the available human judgments to improve summarization systems and evaluat
 ion metrics.\nMaxime comes from France and he received a joint Master's de
 gree in Computer Science from the University of Darmstadt and Grenoble INP
  Ensimag.\nHe then moved to the United Kingdom for one year to work on the
  Alexa project at Amazon Cambridge. For his Ph.D.\, he joined the AIPHES r
 esearch training group from TU Darmstadt focused on Automatic Summarizatio
 n.\n 
LOCATION:BC 333 https://plan.epfl.ch/?room=BC333
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR