Maillette de Buy Wenniger, Gideon, Sima'an, Khalil and Way, Andy ORCID: 0000-0001-5736-5930 (2017) Elastic-substitution decoding for hierarchical SMT: efficiency, richer search and double labels. In: Machine Translation Summit XVI (MT XVI), 18-22 Sep 2017, Nagoya, Japan.
Abstract
Elastic-substitution decoding (ESD), first introduced by Chiang (2010), can be important for obtaining good results when applying labels to enrich hierarchical statistical machine translation (SMT). However, an efficient implementation is essential for scalable application. We describe how to achieve this, contributing essential details that were missing in the original exposition. We compare ESD to strict matching and show its superiority for both reordering and syntactic labels. To overcome the sub-optimal performance due to the late evaluation of features marking label substitution types, we increase the diversity of the rules explored during cube pruning initialization with respect to labels their labels. This approach gives significant improvements over basic ESD and performs favorably compared to extending the search by increasing the cube pruning pop-limit. Finally, we look at combining multiple labels. The combination of reordering labels and target-side boundary-tags yields a significant improvement in terms of the word-order sensitive metrics Kendall reordering score and METEOR. This confirms our intuition that the combination of reordering labels and syntactic labels can yield improvements over either label by itself, despite increased sparsity.
Metadata
Item Type: | Conference or Workshop Item (Paper) |
---|---|
Event Type: | Conference |
Refereed: | Yes |
Uncontrolled Keywords: | Hierarchical Statistical Machine Translation |
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 > Advanced Processing Technology Research Centre (APTRC) Research Initiatives and Centres > ADAPT |
Published in: | Proceedings of MT Summit XVI. 1. |
Official URL: | http://aamt.info/app-def/S-102/mtsummit/2017/confe... |
Copyright Information: | © 2017 The Authors |
Use License: | This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License |
Funders: | ADAPT Centre for Digital Content Technology, funded under SFI Research Centres Programme (Grant 13/RC/2106)., European Union’s Horizon 2020 research and innovation programme under the Marie Marie Skłodowska-Curie grant agreement No 713567., The Netherlands Organization for Scientific Research (NWO) under grant nr. 612.066.929 and VICI grant nr. 277-89-002 and Stichting voor de Technische Wetenschappen (STW) grant nr. 12271. |
ID Code: | 22303 |
Deposited On: | 29 Mar 2018 08:44 by Gideon Maillette De buy . Last Modified 13 Mar 2019 13:49 |
Documents
Full text available as:
Preview |
PDF (Elastic-substitution decoding for Hierarchical SMT: efficiency, richer search and double labels)
- Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
1MB |
Downloads
Downloads
Downloads per month over past year
Archive Staff Only: edit this record