Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

3-2024

Abstract

In this paper, we re-examine the Markov property in the context of neural machine translation. We design a Markov Autoregressive Transformer (MAT) and undertake a comprehensive assessment of its performance across four WMT benchmarks. Our findings indicate that MAT with an order larger than 4 can generate translations with quality on par with that of conventional autoregressive transformers. In addition, counter-intuitively, we also find that the advantages of utilizing a higher-order MAT do not specifically contribute to the translation of longer sentences.

Discipline

Numerical Analysis and Scientific Computing

Research Areas

Data Science and Engineering

Publication

EACL 2024: 18th Conference of the European Chapter of the Association for Computational Linguistics, Findings: St Julian's, Malta, March 17-22

First Page

582

Last Page

588

ISBN

9798891760936

Publisher

Association for Computational Linguistics (ACL)

City or Country

St. Julian's

Copyright Owner and License

Authors

Additional URL

https://aclanthology.org/2024.findings-eacl.40

Share

COinS