Batch Tuning Strategies for Statistical Machine Translation 论文

摘要

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. 1