Exploiting Semantics in Neural Machine Translation with Graph Convolutional Networks

Diego Marcheggiani, Jasmijn Bastings, Ivan Titov


Abstract
Semantic representations have long been argued as potentially useful for enforcing meaning preservation and improving generalization performance of machine translation methods. In this work, we are the first to incorporate information about predicate-argument structure of source sentences (namely, semantic-role representations) into neural machine translation. We use Graph Convolutional Networks (GCNs) to inject a semantic bias into sentence encoders and achieve improvements in BLEU scores over the linguistic-agnostic and syntax-aware versions on the English–German language pair.
Anthology ID:
N18-2078
Original:
N18-2078v1
Version 2:
N18-2078v2
Volume:
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)
Month:
June
Year:
2018
Address:
New Orleans, Louisiana
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
486–492
Language:
URL:
https://aclanthology.org/N18-2078
DOI:
10.18653/v1/N18-2078
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/N18-2078.pdf
Note:
 N18-2078.Notes.pdf
Data
WMT 2016