diff --git a/.gitmodules b/.gitmodules
index 2d98367544ef89ddfb7ecd61e1414ec4a940997f..99a1bbf2457b67c894fccfb654004248560533d5 100644
--- a/.gitmodules
+++ b/.gitmodules
@@ -4,3 +4,6 @@
 [submodule "PaddleNLP/language_representations_kit"]
 	path = PaddleNLP/language_representations_kit
 	url = https://github.com/PaddlePaddle/LARK
+[submodule "knowledge-driven-dialogue"]
+	path = knowledge-driven-dialogue
+	url = https://github.com/baidu/knowledge-driven-dialogue
diff --git a/README.md b/README.md
index a988c861359a2464e29bd4bc5b7085cbf3060ff9..dd48a161bdbf4cf44ada0a81a0975f511c7d91fe 100644
--- a/README.md
+++ b/README.md
@@ -41,6 +41,7 @@ PaddlePaddle 提供了丰富的计算单元，使得用户可以采用模块化
 --|:--:|:--:|:--:
 [Transformer](./PaddleNLP/neural_machine_translation/transformer/README.md)|机器翻译模型|基于self-attention，计算复杂度小，并行度高，容易学习长程依赖，翻译效果更好|[Attention Is All You Need](https://arxiv.org/abs/1706.03762)
 [BERT](https://github.com/PaddlePaddle/LARK/tree/develop/BERT)|语义表示模型|在多个 NLP 任务上取得 SOTA 效果，支持多卡多机训练，支持混合精度训练|[BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://arxiv.org/abs/1810.04805)
+[ERNIE](https://github.com/PaddlePaddle/LARK/tree/develop/ERNIE)|语义表示模型|基于知识增强的中文语义表示模型，在多个任务上的效果超越 BERT 中文模型|-
 [ELMo](https://github.com/PaddlePaddle/LARK/tree/develop/ELMo)|语义表示模型|支持多卡训练，训练速度比主流实现快1倍，提供在中文词法分析任务上迁移学习的示例。|[ELMo: Embeddings from Language Models](https://arxiv.org/abs/1802.05365)
 [LAC](https://github.com/baidu/lac/blob/master/README.md)|联合的词法分析模型|能够整体性地完成中文分词、词性标注、专名识别任务|[Chinese Lexical Analysis with Deep Bi-GRU-CRF Network](https://arxiv.org/abs/1807.01882)
 [Senta](https://github.com/baidu/Senta/blob/master/README.md)|情感倾向分析模型集|百度AI开放平台中情感倾向分析模型|-
diff --git a/PaddleNLP/knowledge-driven-dialogue b/knowledge-driven-dialogue
similarity index 100%
rename from PaddleNLP/knowledge-driven-dialogue
rename to knowledge-driven-dialogue