Fast Neural Machine Translation Implementation
This paper describes the submissions to the efficiency track for GPUs at the Workshop for Neural Machine Translation and Generation by members of the University of Edinburgh, Adam Mickiewicz University, Tilde and University of Alicante. We focus on efficient implementation of the recurrent deep-learning model as implemented in Amun, the fast inference engine for neural machine translation. We improve the performance with an efficient mini-batching algorithm, and by fusing the softmax operation with the k-best extraction algorithm. Submissions using Amun were first, second and third fastest in the GPU efficiency track.
Code (0)
등록된 구현이 없습니다.
Tasks
GPUMachine TranslationTranslationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Sockeye 3: Fast Neural Machine Translation with PyTorch
Sockeye 3 is the latest version of the Sockeye toolkit for Neural Machine Translation (NMT). Now based on PyTorch, Sockeye 3 provides faster model implementations and more advanced features with a further streamlined cod…
Machine TranslationNMTTranslationFast, Scalable Phrase-Based SMT Decoding
The utilization of statistical machine translation (SMT) has grown enormously over the last decade, many using open-source software developed by the NLP community. As commercial use has increased, there is need for softw…
DecoderMachine TranslationTranslationKyoto-NMT: a Neural Machine Translation implementation in Chainer
We present Kyoto-NMT, an open-source implementation of the Neural Machine Translation paradigm. This implementation is done in Python and Chainer, an easy-to-use Deep Learning Framework.
Deep LearningLanguage ModelingLanguage ModellingMachine Translation+2FastWave: Accelerating Autoregressive Convolutional Neural Networks on FPGA
Autoregressive convolutional neural networks (CNNs) have been widely exploited for sequence generation tasks such as audio synthesis, language modeling and neural machine translation. WaveNet is a deep autoregressive CNN…
Audio GenerationAudio SynthesisCPUGPU+4Speeding up Transformer Decoding via an Attention Refinement Network
Despite the revolutionary advances made by Transformer in Neural Machine Translation (NMT), inference efficiency remains an obstacle due to the heavy use of attention operations in auto-regressive decoding. We thereby pr…
Machine TranslationNMTTranslation