Sharing Attention Weights for Fast Transformer
원문 초록
Recently, the Transformer machine translation system has shown strong results by stacking attention layers on both the source and target-language sides. But the inference of this model is slow due to the heavy use of dot-product attention in auto-regressive decoding. In this paper we speed up Transformer via a fast and lightweight attention model. More specifically, we share attention weights in adjacent layers and enable the efficient re-use of hidden states in a vertical manner. Moreover, the sharing policy can be jointly learned with the MT model. We test our approach on ten WMT and NIST OpenMT tasks. Experimental results show that it yields an average of 1.3X speed-up (with almost no decrease in BLEU) on top of a state-of-the-art implementation that has already adopted a cache for fast inference. Also, our approach obtains a 1.8X speed-up when it works with the \textsc{Aan} model. This is even 16 times faster than the baseline with no use of the attention cache.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
CycleDistill: Bootstrapping Machine Translation using LLMs with Cyclical Distillation
Gender Bias in English-to-Greek Machine Translation
TACTIC: Translation Agents with Cognitive-Theoretic Interactive Collaboration
Translate With Care: Addressing Gender Bias, Neutrality, and Reasoning in Large Language Model Translations
Should I Share this Translation? Evaluating Quality Feedback for User Reliance on Machine Translation
Unsupervised Word-level Quality Estimation for Machine Translation Through the Lens of Annotators (Dis)agreement
토론
이 논문과 연결된 포럼 글이 아직 없습니다.