paper-with-me

홈 › Papers

Distilling Multiple Domains for Neural Machine Translation

2020-11-01 · EMNLP 2020 11 · Anna Currey, Prashant Mathur, Georgiana Dinu

Neural machine translation achieves impressive results in high-resource conditions, but performance often suffers when the input domain is low-resource. The standard practice of adapting a separate model for each domain of interest does not scale well in practice from both a quality perspective (brittleness under domain shift) as well as a cost perspective (added maintenance and inference complexity). In this paper, we propose a framework for training a single multi-domain neural machine translation model that is able to translate several domains without increasing inference time or memory usage. We show that this model can improve translation on both high- and low-resource domains over strong multi-domain baselines. In addition, our proposed model is effective when domain labels are unknown during training, as well as robust under noisy data conditions.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationTranslation

Similar Papers 제목 키워드 기반

Distill, Adapt, Distill: Training Small, In-Domain Models for Neural Machine Translation

2020-03-05 · WS 2020 7 · Mitchell A. Gordon, Kevin Duh

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

Look Backward and Forward: Self-Knowledge Distillation with Bidirectional Decoder for Neural Machine Translation

2022-03-10 · Xuanwei Zhang, Libin Shen, Disheng Pan, Liang Wang 외

Neural Machine Translation(NMT) models are usually trained via unidirectional decoder which corresponds to optimizing one-step-ahead prediction. However, this kind of unidirectional decoding framework may incline to focu…

DecoderKnowledge DistillationMachine TranslationNMT+2

Multi-Domain Neural Machine Translation

2018-05-06 · Sander Tars, Mark Fishel

We present an approach to neural machine translation (NMT) that supports multiple domains in a single model and allows switching between the domains when translating. The core idea is to treat text domains as distinct la…

Machine TranslationNMTTranslation

Multi-domain Adaptation for Statistical Machine Translation Based on Feature Augmentation

2016-10-01 · AMTA 2016 10 · Kenji Imamura, Eiichiro Sumita

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 TranslationTranslation

DiMS: Distilling Multiple Steps of Iterative Non-Autoregressive Transformers for Machine Translation

2022-06-07 · Sajad Norouzi, Rasa Hosseinzadeh, Felipe Perez, Maksims Volkovs

The computational benefits of iterative non-autoregressive transformers decrease as the number of decoding steps increases. As a remedy, we introduce Distill Multiple Steps (DiMS), a simple yet effective distillation tec…

de-enMachine TranslationTranslation