Update README

Author: ZeyuChen

README_cn.md

@@ -38,10 +38,10 @@
   </div>
 
 * 🔥 2022.5.16 [**PaddleNLP v2.3**](https://github.com/PaddlePaddle/PaddleNLP/releases/tag/v2.3.0)全新发布！🎉
-  * 🔥 通用信息抽取技术[**UIE**](./model_zoo/uie)发布，单个模型可以同时支持命名实体识别、关系抽取、事件抽取、情感分析等任务。
-  * 🔥 开源文心大模型[**ERNIE 3.0**](./model_zoo/ernie-3.0)轻量级模型，在CLUE Benchmark上实现同规模结构效果最佳。
+  * 💎 通用信息抽取技术[**UIE**](./model_zoo/uie)发布，单个模型可以同时支持命名实体识别、关系抽取、事件抽取、情感分析等任务。
+  * 😊 开源文心大模型[**ERNIE 3.0**](./model_zoo/ernie-3.0)轻量级模型，在CLUE上实现同规模结构效果最佳，并提供 **🗜️无损压缩**和**⚙️全场景部署**方案。
   * 🏥 新增中文医疗领域预训练模型[**ERNIE-Health**](./model_zoo/ernie-health)，CBLUE中文医疗信息处理评测冠军模型。
-  * 💬 新增大规模百亿开放域对话预训练模型[**PLATO-XL (11B)**](https://github.com/PaddlePaddle/PaddleNLP/tree/develop/model_zoo/plato-xl) ，并提供⚡FasterGeneration⚡高性能GPU并行推理加速。
+  * 💬 新增大规模百亿开放域对话预训练模型[**PLATO-XL (11B)**](https://github.com/PaddlePaddle/PaddleNLP/tree/develop/model_zoo/plato-xl) ，并提供⚡**FasterGeneration**⚡高性能GPU并行推理加速。
 
 * 2022.12.12 **PaddleNLP v2.2**发布！新增开箱即用的NLP能力[Taskflow](./docs/model_zoo/taskflow.md)！配套语义检索、智能问答、评论观点抽取[产业案例](./applications)，快速搭建端到端NLP系统！配套视频课程[直通车](https://aistudio.baidu.com/aistudio/course/introduce/24902)！
 
@@ -173,14 +173,14 @@ PaddleNLP针对信息抽取、语义检索、智能问答、情感分析等高
 
 #### ❓ 智能问答系统
 
-推出基于语义检索技术的问答系统，支持FAQ问答、说明书问答等多种业务场景。
+基于[🚀RocketQA](https://github.com/PaddlePaddle/RocketQA)技术的检索式问答系统，支持FAQ问答、说明书问答等多种业务场景。
 
 <div align="center">
     <img src="https://user-images.githubusercontent.com/11793384/168514868-1babe981-c675-4f89-9168-dd0a3eede315.gif" width="400">
 </div>
 
 
-更多使用说明请参考[智能问答系统](./applications/question_answering)。
+更多使用说明请参考[智能问答系统](./applications/question_answering)与[文档智能问答](./applications/doc_vqa)
 
 #### 💌 评论观点抽取与情感分析
 

README_en.md

@@ -37,8 +37,8 @@
   </div>
 
 * 🔥 2022.5.16 PaddleNLP [v2.3](https://github.com/PaddlePaddle/PaddleNLP/releases/tag/v2.3.0) Released!🎉
-  * 🔥 Release [**UIE** (Universal Information Extraction)](./model_zoo/uie) technique, which single model can support *NER*, *Relation Extraction*, *Event Extraction* and *Sentiment Anlaysis* simultaneously.
-  * 🔥 Release [**ERNIE 3.0**](./model_zoo/ernie-3.0) light-weight model which achieved better results compared to ERNIE 2.0 on [CLUE](https://www.cluebenchmarks.com/).
+  * 💎 Release [**UIE** (Universal Information Extraction)](./model_zoo/uie) technique, which single model can support *NER*, *Relation Extraction*, *Event Extraction* and *Sentiment Analysis* simultaneously.
+  * 😊 Release [**ERNIE 3.0**](./model_zoo/ernie-3.0) light-weight model achieved better results compared to ERNIE 2.0 on [CLUE](https://www.cluebenchmarks.com/), also including **🗜️lossless model compression** and **⚙️end-to-end deployment**.
   * 🏥 Release [**ERNIE-Health**](./model_zoo/ernie-health), a **SOTA** biomedical pretrained model on [CBLUE](https://github.com/CBLUEbenchmark/CBLUE).
   * 💬 Release [**PLATO-XL**](./model_zoo/plato-xl) with FasterGeneration, which can do fastest parallel inference with 11B model for open domain chatbot.
 
@@ -55,7 +55,7 @@
 
 ### Out-of-Box NLP Toolset
 
-Taskflow aims to provide off-the-shelf NLP pre-built task covering NLU and NLG scenario, in the meanwhile with extreamly fast infernece satisfying industrial applications.
+Taskflow aims to provide off-the-shelf NLP pre-built task covering NLU and NLG technique, in the meanwhile with extreamly fast infernece satisfying industrial scenario.
 
 ![taskflow1](https://user-images.githubusercontent.com/11793384/159693816-fda35221-9751-43bb-b05c-7fc77571dd76.gif)
 
@@ -171,14 +171,14 @@ For more details please refer to [Neural Search](./applications/neural_search).
 
 #### ❓ Question Answering System
 
-We provide question answering pipeline which can support FAQ system, Document-level Visual Question answering system based on [RocketQA](https://github.com/PaddlePaddle/RocketQA) technique.
+We provide question answering pipeline which can support FAQ system, Document-level Visual Question answering system based on [🚀RocketQA](https://github.com/PaddlePaddle/RocketQA).
 
 <div align="center">
     <img src="https://user-images.githubusercontent.com/11793384/168514868-1babe981-c675-4f89-9168-dd0a3eede315.gif" width="400">
 </div>
 
 
-For more details please refer to [Question Answering](./applications/question_answering).
+For more details please refer to [Question Answering](./applications/question_answering) and [Document VQA](./applications/doc_vqa).
 
 
 #### 💌 Opinion Extraction and Sentiment Analysis