BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Pizza & Talk on "Crosslingual Document Embedding as Reduced-Rank R
 idge Regression"
DTSTART:20190619T120000
DTEND:20190619T140000
DTSTAMP:20260407T163637Z
UID:6e860550f1216affd53ea4017eb55656603dc61cd87aa7e145163953
CATEGORIES:Conferences - Seminars
DESCRIPTION:Robert West is an assistant professor of Computer Science at E
 PFL\, where he heads the Data Science Lab. His research aims to understand
 \, predict\, and enhance human behavior in social and information networks
  by developing techniques in data science\, data mining\, network analysis
 \, machine learning\, and natural language processing. He holds a PhD in c
 omputer science from Stanford University.\n \nThe Swisscom Digital Lab fr
 equently organizes Talks and Conferences on digital topics like AI\, machi
 ne learning\, IoT\, blockchain\, data science ...\nFor this new session\, 
 thee SDLab is happy to welcome Robert West from EPFL.\n\nAgenda - June 19t
 h :\n12 PM to 1 PM : Talk\n1PM to 2 PM: Pizza Lunch\n\nFREE EVENT\nLimited
  places - Registration mandatory on https://www.meetup.com/Swisscom-Digit
 al-Lab/\n\nTopic:\nIn this talk\, Robert will introduce Cr5 (Crosslingual 
 reduced-rank ridge regression)\, a method for embedding documents written 
 in any language into a single\, language-independent vector space\, such t
 hat documents can be seamlessly compared across languages. For training\, 
 their approach leverages a multilingual corpus where the same concept is c
 overed in multiple languages\, such as Wikipedia. As opposed to most prior
  methods\, which use pre-trained monolingual word vectors\, post-process t
 hem to make them crosslingual\, and finally average word vectors to obtain
  document vectors\, Cr5 is trained end-to-end and is thus natively crossli
 ngual as well as document-level. Moreover\, since their algorithm uses the
  singular value decomposition as its core operation\, it is highly scalabl
 e. Experiments show that Cr5 achieves state-of-the-art performance on a cr
 osslingual document retrieval task.\n\nBio:\nBob West is an assistant prof
 essor of Computer Science at EPFL\, where he heads the Data Science Lab. H
 is research aims to understand\, predict\, and enhance human behavior in s
 ocial and information networks by developing techniques in data science\, 
 data mining\, network analysis\, machine learning\, and natural language p
 rocessing. He holds a PhD in computer science from Stanford University.\n\
 nhttps://dlab.epfl.ch\n\nLooking forward to welcoming you !\n\nSwisscom Di
 gital Lab\nEPFL innovation Park\, Bât F\, 3rd floor\n1015 Lausanne\n 
LOCATION:QIF 3 110.1 https://plan.epfl.ch/?room=QIF3110.1
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR