Bicici, Ergun, Liu, Qun and Way, Andy ORCID: 0000-0001-5736-5930 (2015) ParFDA for fast deployment of accurate statistical machine translation systems, benchmarks, and statistics. In: EMNLP 2015 10th Workshop on Statistical Machine Translation, 17-18 Sept 2015, Lisbon, Portugal.
Abstract
We build parallel FDA5 (ParFDA) Moses statistical machine translation (SMT) systems for all language pairs in the
workshop on statistical machine translation (Bojar et al., 2015) (WMT15) translation task and obtain results close to the top with an average of 3.176 BLEU points difference using significantly less resources for building SMT systems. ParFDA is a parallel implementation of feature decay algorithms (FDA) developed for fast deployment of accurate SMT systems. ParFDA Moses SMT system we built is able to obtain the top TER performance in French to English translation. We make the data for building ParFDA Moses SMT systems for WMT15 available:
\url{https://github.com/bicici/ParFDAWMT15}.
Metadata
Item Type: | Conference or Workshop Item (Poster) |
---|---|
Event Type: | Workshop |
Refereed: | Yes |
Uncontrolled Keywords: | Statistical Machine Translation |
Subjects: | Computer Science > Machine translating Computer Science > Information retrieval |
DCU Faculties and Centres: | DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing Research Institutes and Centres > ADAPT |
Published in: | Proceedings of EMNLP 2015 10th Workshop on Statistical Machine Translation. . |
Official URL: | http://dx.doi.org/10.18653/v1/W15-3005 |
Copyright Information: | © 2015 ACL |
Use License: | This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License |
Funders: | Science Foundation Ireland as part of the ADAPT research center (www.adaptcentre.ie, 07/CE/I1142) at Dublin City University, Science Foundation Ireland for the project “Monolingual and Bilingual Text Quality Judgments with Translation mance Prediction” (computing.dcu.ie/ ˜ebicici/Projects/TIDA_RTM.html, 13/TIDA/I2740). |
ID Code: | 20881 |
Deposited On: | 29 Oct 2015 12:03 by Mehmet Ergun Bicici . Last Modified 22 Jul 2019 14:14 |
Documents
Full text available as:
Preview |
PDF (ParFDA for Fast Deployment of Accurate \\ Statistical Machine Translation Systems, Benchmarks, and Statistics)
- Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
128kB |
Metrics
Altmetric Badge
Dimensions Badge
Downloads
Downloads
Downloads per month over past year
Archive Staff Only: edit this record