Learning from Post-Editing: Online Model Adaptation for Statistical Machine Translation
Learning from Post-Editing: Online Model Adaptation for Statistical Machine Translation
复制标题
从译后编辑中学习：统计机器翻译的在线模型自适应
DOI：
10.3115/v1/e14-1042
复制
发表时间：
2014
期刊：
影响因子：
--
通讯作者：
A. Lavie
中科院分区：
文献类型：
--
作者：
Michael J. Denkowski;Chris Dyer;A. Lavie
使用机器翻译输出作为人工翻译的起点已经成为机器翻译越来越普遍的应用。我们提出并评估了三种计算效率高的在线方法，用于在后期编辑的机器翻译输出不断返回到系统的情况下更新统计机器翻译系统：(1)从编辑后的内容中添加新的规则到翻译模型中，(2)更新机器翻译系统使用的目标语言的贝叶斯语言模型，(3)用MIRA步骤更新机器翻译系统的判别参数。单独地，这些技术可以大大提高MT质量，甚至在强基线上。此外，当这三种技术同时使用时，我们看到了超加性的改进。
Using machine translation output as a starting point for human translation has become an increasingly common application of MT. We propose and evaluate three computationally efficient online methods for updating statistical MT systems in a scenario where post-edited MT output is constantly being returned to the system: (1) adding new rules to the translation model from the post-edited content, (2) updating a Bayesian language model of the target language that is used by the MT system, and (3) updating the MT system’s discriminative parameters with a MIRA step. Individually, these techniques can substantially improve MT quality, even over strong baselines. Moreover, we see super-additive improvements when all three techniques are used in tandem.