Paper Info
Title
Dual Reconstruction: a Unifying Objective for Semi-Supervised Neural Machine Translation
Abstract
While Iterative Back-Translation and Dual Learning effectively incorporate monolingual training data in neural machine translation, they use different objectives and heuristic gradient approximation strategies, and have not been extensively compared. We introduce a novel dual reconstruction objective that provides a unified view of Iterative Back-Translation and Dual Learning. It motivates a theoretical analysis and controlled empirical study on German-English and Turkish-English tasks, which both suggest that Iterative Back-Translation is more effective than Dual Learning despite its relative simplicity.
Year
DOI
Venue
2020
10.18653/V1/2020.FINDINGS-EMNLP.182
EMNLP
DocType
Volume
Citations 
Conference
2020.findings-emnlp
0
PageRank 
References 
Authors
0.34
0
3
Name
Order
Citations
PageRank
Weijia Xu105.75
Xing Niu213510.15
Marine Carpuat358751.99