@inproceedings{dou-etal-2018-exploiting,
title = "Exploiting Deep Representations for Neural Machine Translation",
author = "Dou, Zi-Yi and
Tu, Zhaopeng and
Wang, Xing and
Shi, Shuming and
Zhang, Tong",
editor = "Riloff, Ellen and
Chiang, David and
Hockenmaier, Julia and
Tsujii, Jun{'}ichi",
booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing",
month = oct # "-" # nov,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/D18-1457/",
doi = "10.18653/v1/D18-1457",
pages = "4253--4262",
abstract = "Advanced neural machine translation (NMT) models generally implement encoder and decoder as multiple layers, which allows systems to model complex functions and capture complicated linguistic structures. However, only the top layers of encoder and decoder are leveraged in the subsequent process, which misses the opportunity to exploit the useful information embedded in other layers. In this work, we propose to simultaneously expose all of these signals with layer aggregation and multi-layer attention mechanisms. In addition, we introduce an auxiliary regularization term to encourage different layers to capture diverse information. Experimental results on widely-used WMT14 English-German and WMT17 Chinese-English translation data demonstrate the effectiveness and universality of the proposed approach."
}
Markdown (Informal)
[Exploiting Deep Representations for Neural Machine Translation](https://preview.aclanthology.org/jlcl-multiple-ingestion/D18-1457/) (Dou et al., EMNLP 2018)
ACL