Reference Language based Unsupervised Neural Machine Translation

Abstract

Exploiting a common language as an auxiliary for better translation has a long tradition in machine translation and lets supervised learning-based machine translation enjoy the enhancement delivered by the well-used pivot language in the absence of a source language to target language parallel corpus. The rise of unsupervised neural machine translation (UNMT) almost completely relieves the parallel corpus curse, though UNMT is still subject to unsatisfactory performance due to the vagueness of the clues available for its core back-translation training. Further enriching the idea of pivot translation by extending the use of parallel corpora beyond the source-target paradigm, we propose a new reference language-based framework for UNMT, RUNMT, in which the reference language only shares a parallel corpus with the source, but this corpus still indicates a signal clear enough to help the reconstruction training of UNMT through a proposed reference agreement mechanism. Experimental results show that our methods improve the quality of UNMT over that of a strong baseline that uses only one auxiliary language, demonstrating the usefulness of the proposed reference language-based UNMT and establishing a good start for the community.

arXiv commentEMNLP 2020, ACL Findings

References in corpus (12)

• Sequence to Sequence Learning with Neural Networks
• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• Convolutional Sequence to Sequence Learning
• Dual Learning for Machine Translation
• MASS: Masked Sequence to Sequence Pre-training for Language Generation
• Word Translation Without Parallel Data
• The Missing Ingredient in Zero-Shot Neural Machine Translation
• Semantics-aware BERT for Language Understanding
• Cross-lingual Pre-training Based Transfer for Zero-shot Neural Machine Translation
• Knowledge Distillation for Multilingual Unsupervised Neural Machine Translation
• Parsing All: Syntax and Semantics, Dependencies and Spans
• Explicit Sentence Compression for Neural Machine Translation

Cited by in corpus (3)

• SJTU-NICT's Supervised and Unsupervised Neural Machine Translation Systems for the WMT20 News Translation Task
• Unsupervised Translation of German--Lower Sorbian: Exploring Training and Novel Transfer Methods on a Low-Resource Language
• Paraphrase Generation as Unsupervised Machine Translation