From 15eddb022ce1beb281777e9ab8807a1bdfa7a76e Mon Sep 17 00:00:00 2001
From: oyjxer <1728722986@qq.com>
Date: Fri, 3 Dec 2021 21:36:25 +0800
Subject: [PATCH] add ernie-m in readme (#772)

Co-authored-by: pangchao04 <pangchao04@baidu.com>
---
 README.en.md      | 14 ++++++++++++++
 README.zh.md      | 14 ++++++++++++++
 ernie-m/README.md |  9 +++++++++
 3 files changed, 37 insertions(+)
 create mode 100644 ernie-m/README.md

diff --git a/README.en.md b/README.en.md
index 911c622..c2a633f 100644
--- a/README.en.md
+++ b/README.en.md
@@ -12,6 +12,9 @@ ERNIE 2.0 builds a strong basic for nearly every NLP tasks: Text Classification,
 
 # News
 
+- Dec.03.2021:
+    - [`ERNIE-M`](https://github.com/PaddlePaddle/ERNIE/tree/repro/ernie-m) models are **avaliable** now!
+
 - May.20.2021:
     - [`ERNIE-Doc`](https://github.com/PaddlePaddle/ERNIE/tree/repro/ernie-doc), [`ERNIE-Gram`](./ernie-gram/), [`ERNIE-ViL`](https://github.com/PaddlePaddle/ERNIE/tree/repro/ernie-vil) models are **avaliable** now!
     - `ERNIE-UNIMO` has been released in [here](https://github.com/PaddlePaddle/ERNIE/tree/repro/ernie-unimo).
@@ -349,6 +352,17 @@ For details about distillation, see [here](./demo/distill/README.md)
 }
 ```
 
+### ERNIE-M
+
+```
+@article{ouyang2020ernie,
+  title={Ernie-m: Enhanced multilingual representation by aligning cross-lingual semantics with monolingual corpora},
+  author={Ouyang, Xuan and Wang, Shuohuan and Pang, Chao and Sun, Yu and Tian, Hao and Wu, Hua and Wang, Haifeng},
+  journal={arXiv preprint arXiv:2012.15674},
+  year={2020}
+}
+```
+
 For full reproduction of paper results, please checkout to `repro` branch of this repo.
 
 ### Communication
diff --git a/README.zh.md b/README.zh.md
index a087240..b4ff277 100644
--- a/README.zh.md
+++ b/README.zh.md
@@ -10,6 +10,9 @@ ERNIE是百度开创性提出的基于知识增强的持续学习语义理解框
 
 # 新闻
 
+- 2021.12.3:
+  - 多语言预训练模型`ERNIE-M` [正式开源](https://github.com/PaddlePaddle/ERNIE/tree/repro/ernie-m)
+
 - 2021.5.20:
    - ERNIE 最新开源四大预训练模型:
       - 多粒度语言知识模型`ERNIE-Gram` [正式开源](./ernie-gram/)
@@ -354,6 +357,17 @@ ids = np.expand_dims(ids, -1) # ids.shape==[BATCH, SEQLEN, 1]
 }
 ```
 
+### ERNIE-M
+
+```
+@article{ouyang2020ernie,
+  title={Ernie-m: Enhanced multilingual representation by aligning cross-lingual semantics with monolingual corpora},
+  author={Ouyang, Xuan and Wang, Shuohuan and Pang, Chao and Sun, Yu and Tian, Hao and Wu, Hua and Wang, Haifeng},
+  journal={arXiv preprint arXiv:2012.15674},
+  year={2020}
+}
+```
+
 若希望复现 paper 中的所有实验，请切换至本repo的`repro`分支。
 
 ### 讨论组
diff --git a/ernie-m/README.md b/ernie-m/README.md
new file mode 100644
index 0000000..1b174ff
--- /dev/null
+++ b/ernie-m/README.md
@@ -0,0 +1,9 @@
+```bash
+ _____ ____  _   _ ___ _____      __       __
+| ____|  _ \| \ | |_ _| ____|    |  \     /  |
+|  _| | |_) |  \| || ||  _| _____| |\\   //| |
+| |___|  _ <| |\  || || |__|_____| | \\_// | |
+|_____|_| \_\_| \_|___|_____|    |_|  \_/  |_|
+```
+
+The `ERNIE-M` (including all our pre-trained models) has been released at [here](https://github.com/PaddlePaddle/ERNIE/tree/repro/ernie-m).
-- 
GitLab