- Author
- Year
- 2018
- host editors
-
M. Walker
H. Ji
A. Stent - Title
- Exploiting Semantics in Neural Machine Translation with Graph Convolutional Networks
- Event
- 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
- Book/source title
- NAACL-HLT 2018 : The 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
- Book/source subtitle
- proceedings of the conference : June 1-June 6, 2018, New Orleans, Louisiana
- Pages (from-to)
- 486–492
- Number of pages
- 7
- Publisher
- Stroudsburg, PA: The Association for Computational Linguistics
- Volume (Publisher)
- 2
- ISBN (electronic)
- 9781948087292
- Document type
- Conference contribution
- Faculty
- Interfacultary Research
- Institute
- Institute for Logic, Language and Computation (ILLC)
- 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.
- URL
- go to publisher's site
- Language
- English
- Note
- Later version also available. - With supplementary notes.
- Persistent Identifier
- https://hdl.handle.net/11245.1/70e17a6a-e7fb-4efc-b8dc-cb497d8343dd
- Downloads
-
N18-2078v2(Other version)
- Supplementary materials
Disclaimer/Complaints regulations
If you believe that digital publication of certain material infringes any of your rights or (privacy) interests, please let the Library know, stating your reasons. In case of a legitimate complaint, the Library will make the material inaccessible and/or remove it from the website. Please Ask the Library, or send a letter to: Library of the University of Amsterdam, Secretariat, Singel 425, 1012 WP Amsterdam, The Netherlands. You will be contacted as soon as possible.