English

Dual Reconstruction: a Unifying Objective for Semi-Supervised Neural Machine Translation

Computation and Language 2020-10-08 v1 Machine Learning

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.

Keywords

Cite

@article{arxiv.2010.03412,
  title  = {Dual Reconstruction: a Unifying Objective for Semi-Supervised Neural Machine Translation},
  author = {Weijia Xu and Xing Niu and Marine Carpuat},
  journal= {arXiv preprint arXiv:2010.03412},
  year   = {2020}
}

Comments

Accepted at Findings of EMNLP 2020

R2 v1 2026-06-23T19:07:50.998Z