Publication: Why neural translations are the right length
Program
KU-Authors
KU Authors
Co-Authors
Shi, Xing
Knight, Kevin
Advisor
Publication Date
Language
English
Journal Title
Journal ISSN
Volume 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:
EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings
Publisher:
Association for Computational Linguistics (ACL)
Keywords:
Subject
Computer engineering