Modeling Localness for Self-Attention Networks
This work addresses a specific bottleneck in neural machine translation by improving local context modeling, which is an incremental advancement for the field.
The paper tackled the problem of enhancing self-attention networks by modeling local context to capture short-range dependencies, resulting in improved performance on Chinese-English and English-German translation tasks.
Self-attention networks have proven to be of profound value for its strength of capturing global dependencies. In this work, we propose to model localness for self-attention networks, which enhances the ability of capturing useful local context. We cast localness modeling as a learnable Gaussian bias, which indicates the central and scope of the local region to be paid more attention. The bias is then incorporated into the original attention distribution to form a revised distribution. To maintain the strength of capturing long distance dependencies and enhance the ability of capturing short-range dependencies, we only apply localness modeling to lower layers of self-attention networks. Quantitative and qualitative analyses on Chinese-English and English-German translation tasks demonstrate the effectiveness and universality of the proposed approach.