Deep Neural Machine Translation with Weakly-Recurrent Units

Mattia A. Di Gangi, Marcello Federico


Abstract
Recurrent neural networks (RNNs) have represented for years the state of the art in neural machine translation. Recently, new architectures have been proposed, which can leverage parallel computation on GPUs better than classical RNNs. Faster training and inference combined with different sequence-to-sequence modeling also lead to performance improvements. While the new models completely depart from the original recurrent architecture, we decided to investigate how to make RNNs more efficient. In this work, we propose a new recurrent NMT architecture, called Simple Recurrent NMT, built on a class of fast and weakly-recurrent units that use layer normalization and multiple attentions. Our experiments on the WMT14 English-to-German and WMT16 English-Romanian benchmarks show that our model represents a valid alternative to LSTMs, as it can achieve better results at a significantly lower computational cost.
Anthology ID:
2018.eamt-main.12
Volume:
Proceedings of the 21st Annual Conference of the European Association for Machine Translation
Month:
May
Year:
2018
Address:
Alicante, Spain
Editors:
Juan Antonio Pérez-Ortiz, Felipe Sánchez-Martínez, Miquel Esplà-Gomis, Maja Popović, Celia Rico, André Martins, Joachim Van den Bogaert, Mikel L. Forcada
Venue:
EAMT
SIG:
Publisher:
Note:
Pages:
139–148
Language:
URL:
https://aclanthology.org/2018.eamt-main.12
DOI:
Bibkey:
Cite (ACL):
Mattia A. Di Gangi and Marcello Federico. 2018. Deep Neural Machine Translation with Weakly-Recurrent Units. In Proceedings of the 21st Annual Conference of the European Association for Machine Translation, pages 139–148, Alicante, Spain.
Cite (Informal):
Deep Neural Machine Translation with Weakly-Recurrent Units (Di Gangi & Federico, EAMT 2018)
Copy Citation:
PDF:
https://aclanthology.org/2018.eamt-main.12.pdf