Skip to main navigation Skip to search Skip to main content

ODE Transformer: An Ordinary Differential Equation-Inspired Model for Sequence Generation

  • Bei Li
  • , Quan Du
  • , Tao Zhou
  • , Yi Jing
  • , Shuhan Zhou
  • , Xin Zeng
  • , Tong Xiao*
  • , Jingbo Zhu
  • , Xuebo Liu
  • , Min Zhang
  • *Corresponding author for this work
  • Northeastern University China
  • NiuTrans Research
  • Harbin Institute of Technology Shenzhen

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Residual networks are an Euler discretization of solutions to Ordinary Differential Equations (ODE). This paper explores a deeper relationship between Transformer and numerical ODE methods. We first show that a residual block of layers in Transformer can be described as a higher-order solution to ODE. Inspired by this, we design a new architecture, ODE Transformer, which is analogous to the Runge-Kutta method that is well motivated in ODE. As a natural extension to Transformer, ODE Transformer is easy to implement and efficient to use. Experimental results on the large-scale machine translation, abstractive summarization, and grammar error correction tasks demonstrate the high genericity of ODE Transformer. It can gain large improvements in model performance over strong baselines (e.g., 30.77 and 44.11 BLEU scores on the WMT'14 English-German and English-French benchmarks) at a slight cost in inference efficiency.

Original languageEnglish
Title of host publicationACL 2022 - 60th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
EditorsSmaranda Muresan, Preslav Nakov, Aline Villavicencio
PublisherAssociation for Computational Linguistics (ACL)
Pages8335-8351
Number of pages17
ISBN (Electronic)9781955917216
DOIs
StatePublished - 2022
Externally publishedYes
Event60th Annual Meeting of the Association for Computational Linguistics, ACL 2022 - Dublin, Ireland
Duration: 22 May 202227 May 2022

Publication series

NameProceedings of the Annual Meeting of the Association for Computational Linguistics
Volume1
ISSN (Print)0736-587X

Conference

Conference60th Annual Meeting of the Association for Computational Linguistics, ACL 2022
Country/TerritoryIreland
CityDublin
Period22/05/2227/05/22

Fingerprint

Dive into the research topics of 'ODE Transformer: An Ordinary Differential Equation-Inspired Model for Sequence Generation'. Together they form a unique fingerprint.

Cite this