arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1604.05073cs.CL
收藏

基于贝叶斯优化的统计机器翻译速度约束优化

Speed-Constrained Tuning for Statistical Machine Translation Using Bayesian Optimization

University of Sheffield(谢菲尔德大学);SDL Research(SDL研究院)

Daniel Beck, Adrià de Gispert, Gonzalo Iglesias, Aurelien Waite, Bill Byrne

摘要:

我们解决的问题,自动找到的统计机器翻译系统,最大化BLEU分数,同时确保解码速度超过最小值的参数。我们建议使用贝叶斯优化,以有效地调整速度相关的解码参数,很容易将速度作为一个嘈杂的约束函数。所获得的参数值保证满足具有相关联的置信度的速度约束。在三种语言对和两个速度约束值,我们报告整体优化时间减少相比,网格和随机搜索。我们还表明,贝叶斯优化可以解耦速度和BLEU测量,从而进一步减少整体优化时间,因为速度是在一小部分句子上测量的。

英文摘要:

We address the problem of automatically finding the parameters of a statistical machine translation system that maximize BLEU scores while ensuring that decoding speed exceeds a minimum value. We propose the use of Bayesian Optimization to efficiently tune the speed-related decoding parameters by easily incorporating speed as a noisy constraint function. The obtained parameter values are guaranteed to satisfy the speed constraint with an associated confidence margin. Across three language pairs and two speed constraint values, we report overall optimization time reduction compared to grid and random search. We also show that Bayesian Optimization can decouple speed and BLEU measurements, resulting in a further reduction of overall optimization time as speed is measured over a small subset of sentences.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑