upgrade README for paddlenlp 2.0

README.md

@@ -12,18 +12,19 @@
 
 ## 简介
 
-PaddleNLP 2.0拥有丰富的模型库、简洁易用的API与高性能的分布式训练的能力，旨在为飞桨开发者提升文本建模效率，并提供基于PaddlePaddle 2.0的NLP领域最佳实践。
+PaddleNLP 2.0拥有**覆盖多场景的模型库**、**简洁易用的全流程API**与**动静统一的高性能分布式训练**能力，旨在为飞桨开发者提升文本领域建模效率，并提供基于PaddlePaddle 2.0的NLP领域最佳实践。
 
 ## 特性
 
-- **丰富的模型库**
-  - 涵盖了NLP主流应用相关的前沿模型，包括中文词向量、预训练模型、词法分析、文本分类、文本匹配、文本生成、机器翻译、通用对话、问答系统等，更多详细介绍请查看[PaddleNLP模型库](./docs/model_zoo.md)。
+- **覆盖多场景的模型库**
+  - PaddleNLP集成了RNN与Transformer等多种主流模型结构，涵盖从[词向量](./exmaples/word_embedding)、[词法分析](./examples/lexical_analysis/)、[命名实体识别](./examples/named_entity_recognition/)、[语义表示](./examples/language_model)等NLP基础技术，到[文本分类](./examples/text_classification)、[文本匹配](./examples/text_matching)、[文本生成](./examples/text_generation)、[文本图学习](./examples/text_graph/erniesage/README.md)等NLP核心技术。同时针对[机器翻译](./examples/machine_translation)、[通用对话](./examples/dialogue/)、[阅读理解](./exampels/machine_reading_comprehension/)等系统应用提供相应核心组件与预训练模型。更多详细介绍请查看[PaddleNLP应用示例](./examples/)。
 
-- **简洁易用的API**
-  - 深度兼容飞桨2.0的高层API体系，提供可复用的文本建模模块，可大幅度减少数据处理、组网、训练环节的代码开发量，提升文本建模开发效率。
 
-- **高性能分布式训练**
-  - 通过深度优化的混合精度训练策略与Fleet分布式训练API，可充分利用GPU集群资源，高效完成大规模预训练模型的分布式训练。
+- **简洁易用的全流程API**
+  - 深度兼容飞桨2.0的[高层API](https://www.paddlepaddle.org.cn/documentation/docs/zh/tutorial/quick_start/high_level_api/high_level_api.html)体系，内置可复用的文本建模模块([Embedding](./docs/embeddings.md), [CRF](./paddlenlp/layers/crf.py), [Seq2Vec](./paddlenlp/seq2vec/crf.py), [Transformer](./docs/transformers.md))，可大幅度减少在数据处理、模型组网、训练与评估、推理部署环节的开发量，提升NLP任务迭代与落地的效率。
+
+- **动静统一的高性能分布式训练**
+  - 基于飞桨2.0核心框架『动静统一』的特性与领先的混合精度优化策略，结合Fleet分布式训练API，可充分利用GPU集群资源，高效完成大规模预训练模型的分布式训练。
 
 
 ## 安装
@@ -81,10 +82,10 @@ gpt2 = GPT2ForPretraining.from_pretrained('gpt2-base-cn')
 ## 模型库及其应用
 
 PaddleNLP模型库整体介绍请参考文档[PaddleNLP Model Zoo](./docs/model_zoo.md).
-模型应用场景介绍请参考[PaddleNLP Examples](./examples/README.md)。
+模型应用场景介绍请参考[PaddleNLP Examples](./examples/)。
 
-- [词向量](./examples/word_embedding/README.md)
-- [词法分析](./examples/lexical_analysis/README.md)
+- [词向量](./examples/word_embedding/)
+- [词法分析](./examples/lexical_analysis/)
 - [语言模型](./examples/language_model)
 - [文本分类](./examples/text_classification/README.md)
 - [文本生成](./examples/text_generation/README.md)
@@ -108,7 +109,7 @@ PaddleNLP模型库整体介绍请参考文档[PaddleNLP Model Zoo](./docs/model_
 - [Dataset API](./docs/datasets.md)
   * 数据集相关API，包含自定义数据集，数据集贡献与数据集快速加载等功能说明。
 - [Embedding API](./docs/embeddings.md)
-  * 词向量相关API，支持一键快速加载包预训练的中文词向量，VisualDL高维可视化等功能说明。
+  * 词向量相关API，支持一键快速加载包预训练的中文词向量，VisulDL高维可视化等功能说明。
 - [Metrics API](./docs/metrics.md)
   * 针对NLP场景的评估指标说明，与飞桨2.0框架高层API兼容。
 

README_en.md

@@ -12,21 +12,19 @@ English | [简体中文](./README.md)
 
 ## Introduction
 
-PaddleNLP aims to accelerate NLP applications through powerful model zoo, easy-to-use API with detailed tutorials. It's also the NLP best practice for PaddlePaddle 2.0 API system.
+PaddleNLP aims to accelerate NLP applications through powerful model zoo, easy-to-use API and high performance distributed training. It's also the NLP best practice for PaddlePaddle 2.0 API system.
 
 ## Features
 
 * **Rich and Powerful Model Zoo**
   - Our Model Zoo covers mainstream NLP applications, including Lexical Analysis, Syntactic Parsing, Machine Translation, Text Classification, Text Generation, Text Matching, General Dialogue and Question Answering etc.
 
-* **Easy-to-use API**
+* **Easy-to-use and End-to-End API**
   - The API is fully integrated with PaddlePaddle high-level API system. It minimizes the number of user actions required for common use cases like data loading, text pre-processing, training and evaluation. which enables you to deal with text problems more productively.
 
-* **High Performance and Large-scale Training**
-  - We provide a highly optimized ditributed training implementation for BERT with Fleet API, it can fully utilize GPU clusters for large-scale model pre-training. Please refer to our [benchmark](./benchmark/bert) for more information.
+* **High Performance and Distributed Training**
+-  We provide a highly optimized ditributed training implementation for BERT with Fleet API, bnd based the mixed precision training strategy based on PaddlePaddle 2.0, it can fully utilize GPU clusters for large-scale model pre-training.
 
-* **Detailed Tutorials and Industrial Practices**
-  - We offers detailed and interactable notebook tutorials to show you the best practices of PaddlePaddle 2.0.
 
 ## Installation
 
@@ -64,16 +62,18 @@ wordemb.cosine_sim("艺术", "火车")
 
 ### Rich Chinsese Pre-trained Models
 
+
 ```python
-from paddlenlp.transformers import ErnieModel, BertModel, RobertaModel, ElectraModel
+from paddlenlp.transformers import ErnieModel, BertModel, RobertaModel, ElectraModel, GPT2ForPretraining
 
 ernie = ErnieModel.from_pretrained('ernie-1.0')
 bert = BertModel.from_pretrained('bert-wwm-chinese')
 roberta = RobertaModel.from_pretrained('roberta-wwm-ext')
 electra = ElectraModel.from_pretrained('chinese-electra-small')
+gpt2 = GPT2ForPretraining.from_pretrained('gpt2-base-cn')
 ```
 
-For more pretrained model selection, please refer to [Pretrained-Models](./paddlenlp/transformers/README.md)
+For more pretrained model selection, please refer to [Pretrained-Models](./docs/transformers.md)
 
 ## Model Zoo and Applications
 
@@ -89,6 +89,10 @@ For more pretrained model selection, please refer to [Pretrained-Models](./paddl
 - [Machine Translation](./exmaples/machine_translation)
 - [Question Answering](./exmaples/machine_reading_comprehension)
 
+## Advanced Application
+
+- [Model Compression](./examples/model_compression/)
+
 ## API Usage
 
 - [Transformer API](./docs/transformers.md)
@@ -102,13 +106,13 @@ For more pretrained model selection, please refer to [Pretrained-Models](./paddl
 
 Please refer to our official AI Studio account for more interactive tutorials: [PaddleNLP on AI Studio](https://aistudio.baidu.com/aistudio/personalcenter/thirdview/574995)
 
-* [What's Seq2Vec?](https://aistudio.baidu.com/aistudio/projectdetail/1283423) shows how to use LSTM to do sentiment analysis.
+* [What's Seq2Vec?](https://aistudio.baidu.com/aistudio/projectdetail/1283423) shows how to use simple API to finish LSTM model and solve sentiment analysis task.
 
-* [Sentiment Analysis with ERNIE](https://aistudio.baidu.com/aistudio/projectdetail/1294333) shows how to exploit the pretrained ERNIE to make sentiment analysis better.
+* [Sentiment Analysis with ERNIE](https://aistudio.baidu.com/aistudio/projectdetail/1294333) shows how to exploit the pretrained ERNIE to solve sentiment analysis problem.
 
-* [Waybill Information Extraction with BiGRU-CRF Model](https://aistudio.baidu.com/aistudio/projectdetail/1317771) shows how to make use of bigru and crf to do information extraction.
+* [Waybill Information Extraction with BiGRU-CRF Model](https://aistudio.baidu.com/aistudio/projectdetail/1317771) shows how to make use of Bi-GRU plus CRF to finish information extraction task.
 
-* [Waybill Information Extraction with ERNIE](https://aistudio.baidu.com/aistudio/projectdetail/1329361) shows how to exploit the pretrained ERNIE to do information extraction better.
+* [Waybill Information Extraction with ERNIE](https://aistudio.baidu.com/aistudio/projectdetail/1329361) shows how to use ERNIE, the Chinese pre-trained model improve information extraction performance.
 
 
 ## Community