BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Deep Neural Network Applications in Low-Resource Languages
DTSTART:20190712T100000
DTEND:20190712T120000
DTSTAMP:20260412T174324Z
UID:21baa4d04d2e3acd652321a0f45a339c9a90805870e83caf09739cf5
CATEGORIES:Conferences - Seminars
DESCRIPTION:Mohammadreza Banaei\nEDIC candidacy exam\nExam president: Prof
 . Pierre Dillenbourg\nThesis advisor: Prof. Karl Aberer\nCo-examiner: Prof
 . Robert West\n\nAbstract\nIn recent years\, Natural Language Processing (
 NLP) has experienced a considerable leap in the performance of neural mode
 ls in different tasks. However\, most of these novel models rely on extrem
 ely huge unlabeled/labeled corpora\, which are not available for many low-
 resource languages. Our research goal is to design architectures that are 
 able to perform well in low-resource scenarios. As background\, we present
  three papers that are related to our current research objective. The fir
 st paper describes a word segmentation algorithm for handling rare words.
   The second paper proposes an architecture for using phonological featur
 es for transfer learning\, and the last one introduces an algorithm for ge
 nerating enriched word embeddings for low-resource scenarios.\n\nBackgroun
 d papers\nNeural machine translation of rare words with subword units\, by
  R. Sennrich et al.\nPhonologically aware neural model for named entity re
 cognition in low resource transfer settings\, by A. Bharadwaj et al.\nAd
 apting Word Embeddings to New Languageswith Morphological and Phonological
  Subword Representations\, by A. Chaudhary et al.\n\n 
LOCATION:BC 229 https://plan.epfl.ch/?room==BC%20229
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR