BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Textual Information Aggregation from Miscellaneous Sources
DTSTART:20180529T140000
DTEND:20180529T160000
DTSTAMP:20260407T110915Z
UID:766bf125dfbc8a5c742691b6b0aff0ab5227cba7f33b9836e142d91a
CATEGORIES:Conferences - Seminars
DESCRIPTION:Diego Antognini\nEDIC candidacy exam\nExam president: Prof. Ma
 rtin Jaggi\nThesis advisor: Prof. Boi Faltings\nCo-examiner: Prof. Robert 
 West\n\nAbstract\nNowadays\, information from various domains is overwhelm
 ing us from all sides\, whether it comes from medias\, social networks or 
 simply from the web. Moreover\, two contents might share the same semantic
 s but can be expressed in a lot of different ways\, making the process of 
 aggregation even harder. Furthermore\, the elicited information can be eas
 ily altered and propagated. Therefore\, there is a need to develop methods
  for understanding contents or opinions from different documents and deter
 mining if they mean the same\, are different or even contradictory. The ap
 plications of such methods could be information tracing\, multi-document s
 ummarization and many more.\n\nBackground papers\nTowards Coherent Multi-D
 ocument Summarization\, by Christensen C.\, et al.\nGraph Attention Networ
 ks\, by Velickovic P.\, et al.\nEpidemiological Modeling of News and Rumor
 s on Twitter \, by Jin F.\, et al\n 
LOCATION:INR 212 https://plan.epfl.ch/?room=INR212
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR