On The Alignment Problem In Multi-Head Attention-Based Neural Machine Translation

Tamer Alkhouli, Gabriel Bretschner, Hermann Ney


Abstract
This work investigates the alignment problem in state-of-the-art multi-head attention models based on the transformer architecture. We demonstrate that alignment extraction in transformer models can be improved by augmenting an additional alignment head to the multi-head source-to-target attention component. This is used to compute sharper attention weights. We describe how to use the alignment head to achieve competitive performance. To study the effect of adding the alignment head, we simulate a dictionary-guided translation task, where the user wants to guide translation using pre-defined dictionary entries. Using the proposed approach, we achieve up to 3.8% BLEU improvement when using the dictionary, in comparison to 2.4% BLEU in the baseline case. We also propose alignment pruning to speed up decoding in alignment-based neural machine translation (ANMT), which speeds up translation by a factor of 1.8 without loss in translation performance. We carry out experiments on the shared WMT 2016 English→Romanian news task and the BOLT Chinese→English discussion forum task.
Anthology ID:
W18-6318
Volume:
Proceedings of the Third Conference on Machine Translation: Research Papers
Month:
October
Year:
2018
Address:
Brussels, Belgium
Editors:
Ondřej Bojar, Rajen Chatterjee, Christian Federmann, Mark Fishel, Yvette Graham, Barry Haddow, Matthias Huck, Antonio Jimeno Yepes, Philipp Koehn, Christof Monz, Matteo Negri, Aurélie Névéol, Mariana Neves, Matt Post, Lucia Specia, Marco Turchi, Karin Verspoor
Venue:
WMT
SIG:
SIGMT
Publisher:
Association for Computational Linguistics
Note:
Pages:
177–185
Language:
URL:
https://aclanthology.org/W18-6318
DOI:
10.18653/v1/W18-6318
Bibkey:
Cite (ACL):
Tamer Alkhouli, Gabriel Bretschner, and Hermann Ney. 2018. On The Alignment Problem In Multi-Head Attention-Based Neural Machine Translation. In Proceedings of the Third Conference on Machine Translation: Research Papers, pages 177–185, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
On The Alignment Problem In Multi-Head Attention-Based Neural Machine Translation (Alkhouli et al., WMT 2018)
Copy Citation:
PDF:
https://aclanthology.org/W18-6318.pdf