English

Tensor2Tensor for Neural Machine Translation

Machine Learning 2018-03-21 v1 Computation and Language Machine Learning

Abstract

Tensor2Tensor is a library for deep learning models that is well-suited for neural machine translation and includes the reference implementation of the state-of-the-art Transformer model.

Cite

@article{arxiv.1803.07416,
  title  = {Tensor2Tensor for Neural Machine Translation},
  author = {Ashish Vaswani and Samy Bengio and Eugene Brevdo and Francois Chollet and Aidan N. Gomez and Stephan Gouws and Llion Jones and Łukasz Kaiser and Nal Kalchbrenner and Niki Parmar and Ryan Sepassi and Noam Shazeer and Jakob Uszkoreit},
  journal= {arXiv preprint arXiv:1803.07416},
  year   = {2018}
}

Comments

arXiv admin note: text overlap with arXiv:1706.03762

R2 v1 2026-06-23T00:58:51.173Z