English

TranSFormer: Slow-Fast Transformer for Machine Translation

Computation and Language 2023-05-29 v1 Artificial Intelligence

Abstract

Learning multiscale Transformer models has been evidenced as a viable approach to augmenting machine translation systems. Prior research has primarily focused on treating subwords as basic units in developing such systems. However, the incorporation of fine-grained character-level features into multiscale Transformer has not yet been explored. In this work, we present a \textbf{S}low-\textbf{F}ast two-stream learning model, referred to as Tran\textbf{SF}ormer, which utilizes a ``slow'' branch to deal with subword sequences and a ``fast'' branch to deal with longer character sequences. This model is efficient since the fast branch is very lightweight by reducing the model width, and yet provides useful fine-grained features for the slow branch. Our TranSFormer shows consistent BLEU improvements (larger than 1 BLEU point) on several machine translation benchmarks.

Keywords

Cite

@article{arxiv.2305.16982,
  title  = {TranSFormer: Slow-Fast Transformer for Machine Translation},
  author = {Bei Li and Yi Jing and Xu Tan and Zhen Xing and Tong Xiao and Jingbo Zhu},
  journal= {arXiv preprint arXiv:2305.16982},
  year   = {2023}
}

Comments

Accepted by Findings of ACL2023

R2 v1 2026-06-28T10:47:37.468Z