While current state-of-the-art NMT models, such as RNN seq2seq and Transformers, possess a large number of parameters, they are still shallow in comparison to convolutional models used for both text and vision applications. In this work we attempt to train significantly (2-3x) deeper Transformer and Bi-RNN encoders for machine translation. We propose a simple modification to the attention mechanism that eases the optimization of deeper models, and results in consistent gains of 0.7-1.1 BLEU on the benchmark WMT'14 English-German and WMT'15 Czech-English tasks for both architectures.
@article{arxiv.1808.07561,
title = {Training Deeper Neural Machine Translation Models with Transparent Attention},
author = {Ankur Bapna and Mia Xu Chen and Orhan Firat and Yuan Cao and Yonghui Wu},
journal= {arXiv preprint arXiv:1808.07561},
year = {2018}
}