An Empirical Study on Development Set Selection Strategy for Machine Translation Learning
Cong Hui, Hai Zhao, Bao‐Liang Lu, Yan Song · Workshop on Statistical Machine Translation · 2010
This paper describes a statistical machine translation system for our participation for the WMT10 shared task. Based on MOSES, our system is capable of translating German, French and Spanish into English. Our main contribution in this work is about effective parameter tuning. We discover that there is a significant performance gap as different development sets are adopted. Finally, ten groups of development sets are used to optimize the model weights, and this does help us obtain a stable evaluation result.