Neural Machine Translation with Monolingual Translation Memory

Abstract

Prior work has proved that Translation memory (TM) can boost the performance of Neural Machine Translation (NMT). In contrast to existing work that uses bilingual corpus as TM and employs source-side similarity search for memory retrieval, we propose a new framework that uses monolingual memory and performs learnable memory retrieval in a cross-lingual manner. Our framework has unique advantages. First, the cross-lingual memory retriever allows abundant monolingual data to be TM. Second, the memory retriever and NMT model can be jointly optimized for the ultimate translation goal. Experiments show that the proposed method obtains substantial improvements. Remarkably, it even outperforms strong TM-augmented NMT baselines using bilingual TM. Owning to the ability to leverage monolingual data, our model also demonstrates effectiveness in low-resource and domain adaptation scenarios.

arXiv commentACL2021

References in corpus (16)

• Adam: A Method for Stochastic Optimization
• Neural Machine Translation by Jointly Learning to Align and Translate
• Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
• Language Models are Few-Shot Learners
• Dual Learning for Machine Translation
• REALM: Retrieval-Augmented Language Model Pre-Training
• On Using Monolingual Corpora in Neural Machine Translation
• Asymmetric LSH (ALSH) for Sublinear Time Maximum Inner Product Search (MIPS)
• A Survey of Domain Adaptation for Neural Machine Translation
• Revisiting Self-Training for Neural Sequence Generation
• A Retrieve-and-Edit Framework for Predicting Structured Outputs
• Pre-training via Paraphrasing
• TranSmart: A Practical Interactive Machine Translation System
• Nearest Neighbor Machine Translation
• Learning to Reuse Translations: Guiding Neural Machine Translation with Examples
• Self-Training Sampling with Monolingual Data Uncertainty for Neural Machine Translation