Enhancing Machine Translation with Dependency-Aware Self-Attention

Emanuele Bugliarello, Naoaki Okazaki


Abstract
Most neural machine translation models only rely on pairs of parallel sentences, assuming syntactic information is automatically learned by an attention mechanism. In this work, we investigate different approaches to incorporate syntactic knowledge in the Transformer model and also propose a novel, parameter-free, dependency-aware self-attention mechanism that improves its translation quality, especially for long sentences and in low-resource scenarios. We show the efficacy of each approach on WMT English-German and English-Turkish, and WAT English-Japanese translation tasks.
Anthology ID:
2020.acl-main.147
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Editors:
Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1618–1627
Language:
URL:
https://aclanthology.org/2020.acl-main.147
DOI:
10.18653/v1/2020.acl-main.147
Bibkey:
Cite (ACL):
Emanuele Bugliarello and Naoaki Okazaki. 2020. Enhancing Machine Translation with Dependency-Aware Self-Attention. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1618–1627, Online. Association for Computational Linguistics.
Cite (Informal):
Enhancing Machine Translation with Dependency-Aware Self-Attention (Bugliarello & Okazaki, ACL 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-2/2020.acl-main.147.pdf
Video:
 http://slideslive.com/38929162
Code
 e-bug/pascal