Adapting High-resource NMT Models to Translate Low-resource Related Languages without Parallel Data

Abstract

The scarcity of parallel data is a major obstacle for training high-quality machine translation systems for low-resource languages. Fortunately, some low-resource languages are linguistically related or similar to high-resource languages; these related languages may share many lexical or syntactic structures. In this work, we exploit this linguistic overlap to facilitate translating to and from a low-resource language with only monolingual data, in addition to any parallel data in the related high-resource language. Our method, NMT-Adapt, combines denoising autoencoding, back-translation and adversarial objectives to utilize monolingual data for low-resource adaptation. We experiment on 7 languages from three different language families and show that our technique significantly improves translation into low-resource language compared to other translation baselines.

arXiv commentACL 2021

References in corpus (9)

• Multilingual Denoising Pre-training for Neural Machine Translation
• MASS: Masked Sequence to Sequence Pre-training for Language Generation
• Beyond English-Centric Multilingual Machine Translation
• A Teacher-Student Framework for Zero-Resource Neural Machine Translation
• The Missing Ingredient in Zero-Shot Neural Machine Translation
• Domain-Adversarial Training of Neural Networks
• Cross-lingual Retrieval for Iterative Self-Supervised Training
• Synthetic Data for Neural Machine Translation of Spoken-Dialects
• Cross-lingual Supervision Improves Unsupervised Neural Machine Translation