[Lisa_teatalk] Tea Talk today, May 6th: Junyoung Chung

Jörg Bornschein j.bornschein at gmail.com
Fri May 6 09:46:19 EDT 2016


Hi, everyone,

Junyoung Chung will talk today about recent work on Character-Level Neural
Machine Translation:

A Character-Level Decoder without Explicit Segmentation for Neural Machine
Translation

Who: Junyoung Chung
When: Fri. May 6th, 14:30
Where: AA3195


Abstract: The existing machine translation systems, whether phrase-based or
neural, have relied almost exclusively on word-level modelling with
explicit segmentation. In this paper, we ask a fundamental question: can
neural machine translation generate a character sequence without any
explicit segmentation? To answer this question, we evaluate an
attention-based encoder– decoder with a subword-level encoder and a
character-level decoder on four language pairs–En-Cs, En-De, En-Ru and
En-Fi– using the parallel corpora from WMT’15. Our experiments show that
the models with a character-level decoder outperform the ones with a
subword-level decoder on all of the four language pairs. Furthermore, the
ensembles of neural models with a character-level decoder outperform the
state-of-the-art non-neural machine translation systems on En-Cs, En-De and
En-Fi and perform comparably on En-Ru.
---
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://webmail.iro.umontreal.ca/pipermail/lisa_teatalk/attachments/20160506/6d6dcc43/attachment.html 


More information about the Lisa_teatalk mailing list