arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1807.07520cs.CL
收藏

面向小足迹自然语言理解的统计模型压缩

Statistical Model Compression for Small-Footprint Natural Language Understanding

Alexa Machine Learning, Amazon.com(亚马逊公司Alexa机器学习部门)

Grant P. Strimel, Kanthashree Mysore Sathyendra, Stanislav Peshterliev

摘要:

在本文中,我们研究统计模型压缩应用于自然语言理解(NLU)模型。占用空间小的NLU模型对于在硬件受限的设备上启用离线系统以及减少基于云的系统中的按需模型加载延迟非常重要。为了压缩NLU模型,我们提出了两种主要的技术,参数量化和完美的特征散列。这些技术是对现有模型修剪策略(如L1正则化)的补充。我们在一个大规模的NLU系统上进行了实验。结果表明,与原始模型相比,我们的方法实现了14倍的内存使用减少,预测性能影响最小。

英文摘要:

In this paper we investigate statistical model compression applied to natural language understanding (NLU) models. Small-footprint NLU models are important for enabling offline systems on hardware restricted devices, and for decreasing on-demand model loading latency in cloud-based systems. To compress NLU models, we present two main techniques, parameter quantization and perfect feature hashing. These techniques are complementary to existing model pruning strategies such as L1 regularization. We performed experiments on a large scale NLU system. The results show that our approach achieves 14-fold reduction in memory usage compared to the original models with minimal predictive performance impact.

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。

↑