A Survey of Domain Adaptation for Neural Machine Translation

Abstract

Neural machine translation (NMT) is a deep learning based approach for machine translation, which yields the state-of-the-art translation performance in scenarios where large-scale parallel corpora are available. Although the high-quality and domain-specific translation is crucial in the real world, domain-specific corpora are usually scarce or nonexistent, and thus vanilla NMT performs poorly in such scenarios. Domain adaptation that leverages both out-of-domain parallel corpora as well as monolingual corpora for in-domain translation, is very important for domain-specific translation. In this paper, we give a comprehensive survey of the state-of-the-art domain adaptation techniques for NMT.

COLING 2018, 16 pages, 9 figures

References in corpus (19)

• Distilling the Knowledge in a Neural Network
• 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
• Adversarial Discriminative Domain Adaptation
• Domain Adaptation for Visual Applications: A Comprehensive Survey
• Fast Domain Adaptation for Neural Machine Translation
• Neural Machine Translation and Sequence-to-sequence Models: A Tutorial
• Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation
• Multi-Adversarial Domain Adaptation
• Neural Machine Translation Training in a Multi-Domain Scenario
• Domain specialization: a post-training domain adaptation for Neural Machine Translation
• Incorporating Discrete Translation Lexicons into Neural Machine Translation
• Domain Generalization via Conditional Invariant Representation
• Multiple Source Domain Adaptation with Adversarial Training of Neural Networks
• One Sentence One Model for Neural Machine Translation
• Building a Neural Machine Translation System Using Only Synthetic Parallel Data
• Domain Control for Neural Machine Translation
• Connecting Phrase based Statistical Machine Translation Adaptation

Cited by in corpus (26)

• MetaMT,a MetaLearning Method Leveraging Multiple Domain Data for Low Resource Machine Translation
• Controlling the Output Length of Neural Machine Translation
• Crowdsourcing Learning as Domain Adaptation: A Case Study on Named Entity Recognition
• Neural Machine Translation with Monolingual Translation Memory
• Simple, Scalable Adaptation for Neural Machine Translation
• Literature review on vulnerability detection using NLP technology
• Multi-Domain Adaptation in Neural Machine Translation Through Multidimensional Tagging
• Tag-less Back-Translation
• Curriculum Learning for Domain Adaptation in Neural Machine Translation
• Transductive Data-Selection Algorithms for Fine-Tuning Neural Machine Translation
• A Brief Survey of Multilingual Neural Machine Translation
• Unsupervised Calibration under Covariate Shift
• Multi-Domain Neural Machine Translation with Word-Level Adaptive Layer-wise Domain Mixing
• A Survey on Low-Resource Neural Machine Translation
• Multi-Source Domain Adaptation for Text Classification via DistanceNet-Bandits
• Rapid Domain Adaptation for Machine Translation with Monolingual Data
• Neural Machine Translation: A Review and Survey
• Types of Out-of-Distribution Texts and How to Detect Them
• Robust Machine Translation with Domain Sensitive Pseudo-Sources: Baidu-OSU WMT19 MT Robustness Shared Task System Report
• Domain Adaptation of NMT models for English-Hindi Machine Translation Task at AdapMT ICON 2020
• On the Language Coverage Bias for Neural Machine Translation
• Revisiting Simple Domain Adaptation Methods in Unsupervised Neural Machine Translation
• The ADAPT System Description for the IWSLT 2018 Basque to English Translation Task
• Towards Faster k-Nearest-Neighbor Machine Translation
• Using Machine Translation to Localize Task Oriented NLG Output
• Positioning yourself in the maze of Neural Text Generation: A Task-Agnostic Survey