Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Survey
The development of deep learning techniques has allowed Neural Machine Translation (NMT) models to become extremely powerful, given sufficient training data and training time. However, systems struggle when translating text from a new domain with a distinct style or vocabulary. Fine-tuning on in-domain data allows good domain adaptation, but requires sufficient relevant bilingual data. Even if this is available, simple fine-tuning can cause overfitting to new data and `catastrophic forgetting' of previously learned behaviour. We concentrate on robust approaches to domain adaptation for NMT, particularly where a system may need to translate across multiple domains. We divide techniques into those revolving around data selection or generation, model architecture, parameter adaptation procedure, and inference procedure. We finally highlight the benefits of domain adaptation and multi-domain adaptation techniques to other lines of NMT research.
Code (0)
등록된 구현이 없습니다.
Tasks
Domain AdaptationMachine TranslationNMTTranslationSimilar Papers 제목 키워드 기반
Multilingual Multi-Domain Adaptation Approaches for Neural Machine Translation
In this paper, we propose two novel methods for domain adaptation for the attention-only neural machine translation (NMT) model, i.e., the Transformer. Our methods focus on training a single translation model for multipl…
Domain AdaptationMachine TranslationNMTTranslationMulti-domain Adaptation for Statistical Machine Translation Based on Feature Augmentation
Domain adaptation is a major challenge when applying machine translation to practical tasks. In this paper, we present domain adaptation methods for machine translation that assume multiple domains. The proposed methods …
Domain AdaptationMachine TranslationTranslationTowards a Fine-Grained Multi-Domain Neural Machine Translation Using Inter-Domain Relationships
While research on the domain adaptation task in neural machine translation has become popular recently, there exists no agreement on what constituents a domain, and most previous studies only focus on coarse-grained doma…
Domain AdaptationMachine TranslationTranslationDomain specialization: a post-training domain adaptation for Neural Machine Translation
Domain adaptation is a key feature in Machine Translation. It generally encompasses terminology, domain and style adaptation, especially for human post-editing workflows in Computer Assisted Translation (CAT). With Neura…
Domain AdaptationMachine TranslationNMTTranslationRapid Domain Adaptation for Machine Translation with Monolingual Data
One challenge of machine translation is how to quickly adapt to unseen domains in face of surging events like COVID-19, in which case timely and accurate translation of in-domain information into multiple languages is cr…
Domain AdaptationMachine TranslationTranslation