Logo of Science Foundation Ireland  Logo of the Higher Education Authority, Ireland7 Capacities
Ireland's High-Performance Computing Centre | ICHEC
Home | News | Infrastructure | Outreach | Services | Research | Support | Education & Training | Consultancy | About Us | Login


Title:Parallel FDA5 for Fast Deployment of Accurate Statistical Machine Translation Systems
Authors:Ergun Bicici, Qun Liu, Andy Way, 2014
Abstract: We use parallel FDA5, an efficiently parameterized and optimized parallel implementation of feature decay algorithms for fast deployment of accurate statistical machine translation systems, taking only about half a day for each translation direction. We build Parallel FDA5 Moses SMT systems for all language pairs in the WMT14 translation task and obtain SMT performance close to the top Moses systems with an average of $3.49$ BLEU points difference using significantly less resources for training and development.
ICHEC Project:Large Scale Experiments on Machine Translation Performance Prediction for High Quality Machine Translation
Publication:In Proceedings of the Ninth Workshop on Statistical Machine Translation, pages 59–65, Baltimore, USA. Association for Computational Linguistics.
URL: http://www.statmt.org/wmt14/pdf/W14-3303.pdf
Status: Published

return to publications list