papers AI Learner
The Github is limit! Click to go to the new site.

Convolutional Self-Attention Networks

2019-04-05
Baosong Yang, Longyue Wang, Derek Wong, Lidia S. Chao, Zhaopeng Tu

Abstract

Self-attention networks (SANs) have drawn increasing interest due to their high parallelization in computation and flexibility in modeling dependencies. SANs can be further enhanced with multi-head attention by allowing the model to attend to information from different representation subspaces. In this work, we propose novel convolutional self-attention networks, which offer SANs the abilities to 1) strengthen dependencies among neighboring elements, and 2) model the interaction between features extracted by multiple attention heads. Experimental results of machine translation on different language pairs and model settings show that our approach outperforms both the strong Transformer baseline and other existing models on enhancing the locality of SANs. Comparing with prior studies, the proposed model is parameter free in terms of introducing no more parameters.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1904.03107

PDF

https://arxiv.org/pdf/1904.03107


Similar Posts

Comments