Why Self-Attention? A Targeted Evaluation of Neural Machine Translation Architectures

Gongbo Tang, Mathias Müller, Annette Rios, Rico Sennrich


Abstract
Recently, non-recurrent architectures (convolutional, self-attentional) have outperformed RNNs in neural machine translation. CNNs and self-attentional networks can connect distant words via shorter network paths than RNNs, and it has been speculated that this improves their ability to model long-range dependencies. However, this theoretical argument has not been tested empirically, nor have alternative explanations for their strong performance been explored in-depth. We hypothesize that the strong performance of CNNs and self-attentional networks could also be due to their ability to extract semantic features from the source text, and we evaluate RNNs, CNNs and self-attention networks on two tasks: subject-verb agreement (where capturing long-range dependencies is required) and word sense disambiguation (where semantic feature extraction is required). Our experimental results show that: 1) self-attentional networks and CNNs do not outperform RNNs in modeling subject-verb agreement over long distances; 2) self-attentional networks perform distinctly better than RNNs and CNNs on word sense disambiguation.
Anthology ID:
D18-1458
Volume:
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Month:
October-November
Year:
2018
Address:
Brussels, Belgium
Editors:
Ellen Riloff, David Chiang, Julia Hockenmaier, Jun’ichi Tsujii
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
4263–4272
Language:
URL:
https://aclanthology.org/D18-1458
DOI:
10.18653/v1/D18-1458
Bibkey:
Cite (ACL):
Gongbo Tang, Mathias Müller, Annette Rios, and Rico Sennrich. 2018. Why Self-Attention? A Targeted Evaluation of Neural Machine Translation Architectures. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 4263–4272, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Why Self-Attention? A Targeted Evaluation of Neural Machine Translation Architectures (Tang et al., EMNLP 2018)
Copy Citation:
PDF:
https://aclanthology.org/D18-1458.pdf
Video:
 https://vimeo.com/306131741
Code
 awslabs/sockeye