Setup. We evaluated our approach on Chinese-English and English- French machine translation tasks. For Chinese-English, the training corpus from LDC con- sists of 2.56M sentence pairs with 67.53M Chinese words and 74.81M English words. We used the NIST 2006 dataset as the validation set for hyper-parameter optimization and model se- lection. The NIST 2002, 2003, 2004, 2005, and 2008 datasets were used as test sets. In the NIST Chinese-English datasets, each Chinese sentence has four reference English transla- tions. To build English-Chinese validation and test sets, we simply “reverse” the Chinese-English datasets: the first En- glish sentence in the four references as the source sentence and the Chinese sentence as the single reference translation. For English-French, the training corpus from WMT 2014 consists of 12.07M sentence pairs with 303.88M English words and 348.24M French words. The concatenation of news-test-2012 and news-test-2013 was used as the valida- tion set and news-test-2014 as the test set. Each English sen- tence has a single reference French translation. The French- English evaluation sets can be easily obtained by reversing the English-French datasets. We compared our approach with two state-of-the-art SMT and NMT systems:
Appears in 3 contracts
Sources: Research and Development, Joint Training Agreement, Research and Development