Vanmassenhove, Eva 
ORCID: 0000-0003-1162-820X and Way, Andy ORCID: 0000-0001-5736-5930
(2018)
SuperNMT: neural machine translation with semantic supersenses and
syntactic supertags.
In: ACL 2018, 15 - 20 July 2018, Melbourne, Australia.
Abstract
In this paper we incorporate semantic supersensetags and syntactic supertag features into EN–FR and EN–DE factored
NMT systems. In experiments on various test sets, we observe that such features
(and particularly when combined) help the
NMT model training to converge faster
and improve the model quality according
to the BLEU scores.
Metadata
| Item Type: | Conference or Workshop Item (Paper) |
|---|---|
| Event Type: | Conference |
| Refereed: | Yes |
| Subjects: | Computer Science > Machine translating |
| DCU Faculties and Centres: | DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing Research Initiatives and Centres > ADAPT |
| Published in: | Shwartz, Vered and Tabassum, Jeniya, (eds.) Proceedings of ACL 2018, Student Research Workshop. . Association for Computational Linguistics (ACL). |
| Publisher: | Association for Computational Linguistics (ACL) |
| Official URL: | http://dx.doi.org/10.18653/v1/P18-3010 |
| Copyright Information: | © 2018 Association for Computational Linguistics |
| Use License: | This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License |
| Funders: | Dublin City University Faculty of Engineering & Computing under the Daniel O’Hare Research Schol- 72 arship scheme, ADAPT Centre for Digital Content Technology which is funded under the SFI Research Centres Programme (Grant 13/RC/2106) and is co-funded under the European Regional Development Fund. |
| ID Code: | 23372 |
| Deposited On: | 28 May 2019 15:51 by Thomas Murtagh . Last Modified 06 Jul 2020 14:14 |
Documents
Full text available as:
Preview |
PDF
- Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
238kB |
Downloads
Downloads
Downloads per month over past year
Archive Staff Only: edit this record
Altmetric
Altmetric