Neural Machine Translation by Minimising the Bayes-risk with Respect to Syntactic Translation Lattices

Felix Stahlberg, Adrià de Gispert, Eva Hasler, Bill Byrne


Abstract
We present a novel scheme to combine neural machine translation (NMT) with traditional statistical machine translation (SMT). Our approach borrows ideas from linearised lattice minimum Bayes-risk decoding for SMT. The NMT score is combined with the Bayes-risk of the translation according the SMT lattice. This makes our approach much more flexible than n-best list or lattice rescoring as the neural decoder is not restricted to the SMT search space. We show an efficient and simple way to integrate risk estimation into the NMT decoder which is suitable for word-level as well as subword-unit-level NMT. We test our method on English-German and Japanese-English and report significant gains over lattice rescoring on several data sets for both single and ensembled NMT. The MBR decoder produces entirely new hypotheses far beyond simply rescoring the SMT search space or fixing UNKs in the NMT output.
Anthology ID:
E17-2058
Volume:
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers
Month:
April
Year:
2017
Address:
Valencia, Spain
Editors:
Mirella Lapata, Phil Blunsom, Alexander Koller
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
362–368
Language:
URL:
https://aclanthology.org/E17-2058
DOI:
Bibkey:
Cite (ACL):
Felix Stahlberg, Adrià de Gispert, Eva Hasler, and Bill Byrne. 2017. Neural Machine Translation by Minimising the Bayes-risk with Respect to Syntactic Translation Lattices. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pages 362–368, Valencia, Spain. Association for Computational Linguistics.
Cite (Informal):
Neural Machine Translation by Minimising the Bayes-risk with Respect to Syntactic Translation Lattices (Stahlberg et al., EACL 2017)
Copy Citation:
PDF:
https://aclanthology.org/E17-2058.pdf