Domain adapted machine translation: What does catastrophic forgetting forget and why?
Neural Machine Translation (NMT) models can be specialized by domain adaptation, often involving fine-tuning on a dataset of interest. This process risks catastrophic forgetting: rapid loss of generic translation quality. Forgetting has been widely observed, with many mitigation methods proposed. However, the causes of forgetting and the relationship between forgetting and adaptation data are under-explored. This paper takes a novel approach to understanding catastrophic forgetting during NMT adaptation by investigating the impact of the data. We provide a first investigation of what is forgotten, and why. We examine the relationship between forgetting and the in-domain data, and show that the amount and type of forgetting is linked to that data's target vocabulary coverage. Our findings pave the way toward better informed NMT domain adaptation.
Code (0)
등록된 구현이 없습니다.
Tasks
Domain AdaptationMachine TranslationNMTTranslationSimilar Papers 제목 키워드 기반
Freezing Subnetworks to Analyze Domain Adaptation in Neural Machine Translation
To better understand the effectiveness of continued training, we analyze the major components of a neural machine translation system (the encoder, decoder, and each embedding space) and consider each component's contribu…
DecoderDomain AdaptationMachine TranslationTranslationImpact of Domain-Adapted Multilingual Neural Machine Translation in the Medical Domain
Multilingual Neural Machine Translation (MNMT) models leverage many language pairs during training to improve translation quality for low-resource languages by transferring knowledge from high-resource languages. We stud…
Machine TranslationTranslationCurriculum Learning for Domain Adaptation in Neural Machine Translation
We introduce a curriculum learning approach to adapt generic neural machine translation models to a specific domain. Samples are grouped by their similarities to the domain of interest and each group is fed to the traini…
Domain AdaptationMachine TranslationTranslationBuilding Machine Translation System for Software Product Descriptions Using Domain-specific Sub-corpora Extraction
Building Machine Translation systems for a specific domain requires a sufficiently large and good quality parallel corpus in that domain. However, this is a bit challenging task due to the lack of parallel data in many d…
Machine TranslationSentenceSentence EmbeddingSentence-Embedding+1Distill, Adapt, Distill: Training Small, In-Domain Models for Neural Machine Translation
We explore best practices for training small, memory efficient machine translation models with sequence-level knowledge distillation in the domain adaptation setting. While both domain adaptation and knowledge distillati…
Domain AdaptationKnowledge DistillationMachine TranslationTranslation