NLP

1. Background 2. BERT: higher accuracy and less handcraft Replace manual features Replace classifier for dense feature 3. Scaling with MXNet Model Server Customization Load test 4. Recap In this article, I will give a brief introduction on how to improve intent classification using pre-trained model BERT and MXNet Model Server (MMS).

1. 问题背景 自从 Y. Bengio 的那篇 A neural probabilistic language model 1开始，词向量一直是自然语言处理中将离散化的文字嵌入连续空间的主要方法。而随着近几年深