Document worth reading: “A Survey of Domain Adaptation for Neural Machine Translation”

Neural machine translation (NMT) is a deep learning based technique for machine translation, which yields the state-of-the-art translation effectivity in eventualities the place large-scale parallel corpora might be discovered. Although the high-quality and domain-specific translation is crucial within the true world, domain-specific corpora are usually scarce or nonexistent, and thus vanilla NMT performs poorly in such eventualities. Domain adaptation that leverages every out-of-domain parallel corpora along with monolingual corpora for in-domain translation, is crucial for domain-specific translation. In this paper, we give a whole survey of the state-of-the-art space adaptation methods for NMT. A Survey of Domain Adaptation for Neural Machine Translation