《自然语言处理实战入门》深度学习 ---- 预训练模型的使用（BERT）

---

bert 简介

BERT, or 【Bidirectional Encoder Representations from Transformers】, is a new method of pre-training language representations which obtains state-of-the-art results on a wide array of Natural Language Processing (NLP) tasks.

BERT，或Transformers的双向编码器表示法，是一种新的预训练语言表示法，可在大量自然语言处理（NLP）任务中获得最先进的结果。

BERT 原始论文链接如下：

Our academic paper which describes BERT in detail and provides full results on a number of tasks can be found here: https://arxiv.org/abs/1810.04805.