Paper: Batch Tuning Strategies for Statistical Machine Translation

ACL ID N12-1047
Title Batch Tuning Strategies for Statistical Machine Translation
Venue Annual Conference of the North American Chapter of the Association for Computational Linguistics
Session Main Conference
Year 2012
Authors

There has been a proliferation of recent work on SMT tuning algorithms capable of han- dling larger feature sets than the traditional MERT approach. We analyze a number of these algorithms in terms of their sentence- level loss functions, which motivates several new approaches, including a Structured SVM. We perform empirical comparisons of eight different tuning strategies, including MERT, in a variety of settings. Among other results, we find that a simple and efficient batch ver- sion of MIRA performs at least as well as training online, and consistently outperforms other options.