论文信息 - Parallel FDA5 for Fast Deployment of Accurate Statistical Machine Translation Systems

Parallel FDA5 for Fast Deployment of Accurate Statistical Machine Translation Systems

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.

[1] Philipp Koehn,et al. Moses: Open Source Toolkit for Statistical Machine Translation , 2007, ACL.

[2] Andy Way,et al. The DCU-ICTCAS MT system at WMT 2014 on German-English Translation Task , 2014, WMT@ACL.

[3] Deniz Yuret,et al. Optimizing Instance Selection for Statistical Machine Translation with Feature Decay Algorithms , 2015, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[4] Jian Zhang,et al. Experiments in Medical Translation Shared Task at WMT 2014 , 2014, WMT@ACL.

[5] Deniz Yuret,et al. Instance Selection for Machine Translation using Feature Decay Algorithms , 2011, WMT@EMNLP.

[6] Clifford Stein,et al. Introduction to Algorithms -3/Ed. , 2012 .

[7] Andreas Stolcke,et al. SRILM - an extensible language modeling toolkit , 2002, INTERSPEECH.

[8] Mehmet Ergun Biçici,et al. The Regression Model of Machine Translation , 2012 .

[9] William Lewis,et al. Crisis MT: Developing A Cookbook for MT in Crisis Situations , 2011, WMT@EMNLP.

[10] Ronald L. Rivest,et al. Introduction to Algorithms , 1990 .

[11] Philipp Koehn,et al. Findings of the 2014 Workshop on Statistical Machine Translation , 2014, WMT@ACL.

[12] Ergun Biçici,et al. Feature Decay Algorithms for Fast Deployment of Accurate Statistical Machine Translation Systems , 2013, WMT@ACL.

[13] Hermann Ney,et al. A Systematic Comparison of Various Statistical Alignment Models , 2003, CL.