A Survey of Domain Adaptation for Neural Machine Translation

By Chenhui Chu, Rui Wang. 2018

292 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Natural Language Processing

Citations in the corpus

Simple, Scalable Adaptation for Neural Machine Translation (2019, background): “While several approaches have been explored in literature (Chu and Wang, 2018), full ﬁne-tuning of model parameters remains the dominant approach for adapting to new domains and languages (Luong and Manning, 2015; Neubig and Hu, 2018).”
A Survey of Multilingual Neural Machine Translation (2019, background): “Leveraging out-of-domain parallel corpora and in-domain monolingual corpora for in-domain translation is known as domain adaptation for MT (Chu and Wang, 2018).”
Unsupervised Domain Clusters in Pretrained Language Models (2020, methodology): “For more related work on data selection and domain adaptation in the context of MT, see the surveys by Eetemadi et al. (2015) for SMT and more recently Chu and Wang (2018) for NMT. Unrelated to MT, Ma et al. (2019) used BERT to select data for tasks from the GLUE benchmark (Wang et al., 2018).”
Multi-Domain Neural Machine Translation with Word-Level Adaptive Layer-wise Domain Mixing (2019, background): “Researchers have proposed many methods for improving multi-domain NMT.”
Transfer learning: a friendly introduction (2022, background): “One famous example is Google’s Neural Machine Translational model (GNMT), which considers powerful cross-lingual interpretations.”
Finding Sparse Structures for Domain Specific Neural Machine Translation (2021, background): “These work can be grouped into two categories: data-centric and model ﬁne-tuning (Chu and Wang 2018).”
Can Automatic Post-Editing Improve NMT? (2020, background): “While NMT performance has been known to be particularly domain-dependant (Chu and Wang, 2018), domain shift between NMT and APE training has not been investigated previously.”
Curriculum Learning for Domain Adaptation in Neural Machine Translation (2019, background): “Chu and Wang (2018) surveyed recent domain adaptation methods for NMT.”
Dictionary-based Data Augmentation for Cross-Domain Neural Machine Translation (2020, background): “As IND parallel corpora are scarce, a category of data-centric domain adaptation research for NMT came into shape (Chu and Wang, 2018) focusing on 1) leveraging monolingual IND data (Zhang and Zong, 2016b; Cheng et al., 2016; Currey et al., 2017; Domhan and Hieber, 2017); 2) sentence selection from…”
Neural Machine Translation for Low-resource Languages: A Survey (2021, methodology): “[37], Chu and Wang [29], Gibadullin et al.”
Neural Unsupervised Domain Adaptation in NLP—A Survey (2020, background): “, 2015; Wilson and Cook, 2020), machine translation (MT) (Chu and Wang, 2018), pre-neural DA methods in NLP (Jiang, 2008; Margolis, 2011).”
Neural Machine Translation: A Review (2019, background): “There is a robust body of research on domain adaptation for machine translation [471, 472].”
A Survey of Unsupervised Deep Domain Adaptation (2018, methodology): “Still others are application-centric, focusing on a single use case such as machine translation [24, 42].”
Data Kernel Perspective Space Performance Guarantees for Synthetic Data from Transformer Models (2026, unknown): “The models achieving these impressive results however share a fundamental property with all their other neural and pre-neural forbearers - they perform worse on data that does not resemble their training data ( [20], [21], [22], [23], [24]).”