Self-attentive residual decoder for neural machine translation

Miculicich Werlen, Lesly (Idiap Research Institute, Switzerland ; École polytechnique fédérale de Lausanne (EPFL), Switzerland) ; Pappas, Nikolaos (Idiap Research Institute, Switzerland) ; Ram, Dhananjay (Idiap Research Institute, Switzerland ; Ecole polytechnique fédérale de Lausanne (EPFL), Switzerland) ; Popescu-Belis, Andrei (School of Management and Engineering Vaud, HES-SO // University of Applied Sciences Western Switzerland)

Neural sequence-to-sequence networks with attention have achieved remarkable performance for machine translation. One of the reasons for their effectiveness is their ability to capture relevant source-side contextual information at each time-step prediction through an attention mechanism. However, the target-side context is solely based on the sequence model which, in practice, is prone to a recency bias and lacks the ability to capture effectively nonsequential dependencies among words. To address this limitation, we propose a target-sideattentive residual recurrent network for decoding, where attention over previous words contributes directly to the prediction of the next word. The residual learning facilitates the flow of information from the distant past and is able to emphasize any of the previously translated words, hence it gains access to a wider context. The proposed model outperforms a neural MT baseline as well as a memory and self-attention network on three language pairs. The analysis of the attention learned by the decoder confirms that it emphasizes a wider context, and that it captures syntactic-like structures.


Keywords:
Conference Type:
full paper
Faculty:
Ingénierie et Architecture
School:
HEIG-VD
Institute:
IICT - Institut des Technologies de l'Information et de la Communication
Subject(s):
Ingénierie
Publisher:
New Orleans, USA, 1-6 June
Date:
New Orleans, USA
1-6 June
2018
Pagination:
14 p.
Published in:
Proceedings of the 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Numeration (vol. no.):
2018
Appears in Collection:

Note: The status of this file is: restricted


 Record created 2018-05-22, last modified 2019-03-12

Fulltext:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)