Papers › Rethinking Zero-shot Neural Machine Translation: From a Perspective of Latent Variables

Rethinking Zero-shot Neural Machine Translation: From a Perspective of Latent Variables

10 Sep 2021Findings (EMNLP) 2021 11arXiv:2109.04705archive 2025-07-28

Weizhi Wang, Zhirui Zhang, Yichao Du, Boxing Chen, Jun Xie, Weihua Luo

Zero-shot translation, directly translating between language pairs unseen in training, is a promising capability of multilingual neural machine translation (NMT). However, it usually suffers from capturing spurious correlations between the output language and language invariant semantics due to the maximum likelihood training objective, leading to poor transfer performance on zero-shot translation. In this paper, we introduce a denoising autoencoder objective based on pivot language into traditional training objective to improve the translation accuracy on zero-shot directions. The theoretical analysis from the perspective of latent variables shows that our approach actually implicitly maximizes the probability distributions for zero-shot directions. On two benchmark machine translation datasets, we demonstrate that the proposed method is able to effectively eliminate the spurious correlations and significantly outperforms state-of-the-art methods with a remarkable performance. Our code is available at https://github.com/Victorwz/zs-nmt-dae.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

victorwz/zs-nmt-dae officialmentioned in papermentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

DenoisingMachine TranslationNMTTranslation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Denoising Autoencoder

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections