Publication: Why neural translations are the right length
Loading...
Program
KU-Authors
Organization Authors
Co-Authors
Shi, Xing
Knight, Kevin
Date
Language
Embargo Status
No
Journal Title
Journal ISSN
Volume Title
Alternative Title
Abstract
We investigate how neural, encoder-decoder translation systems output target strings of appropriate lengths, finding that a collection of hidden units learns to explicitly implement this functionality.
Source
Publisher
Association for Computational Linguistics (ACL)
Subject
Citation
item.page.haspartof
Source
EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings
item.page.ispartofseries
item.page.edition
DOI
10.18653/v1/d16-1248
item.page.datauri
item.page.link
Rights
CC BY (Attribution)
Copyrights Note
Creative Commons license
Except where otherwise noted, this item's license is described as CC BY (Attribution)

