Skip to content

Commit a34f689

Browse files
ZeyuChenZeyuChen
committed
Update English docs
1 parent e51e699 commit a34f689

File tree

3 files changed

+65
-38
lines changed

3 files changed

+65
-38
lines changed

‎README.md‎

Lines changed: 2 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -22,10 +22,10 @@
2222
PaddleNLP是飞桨自然语言处理开发库，具备**易用的文本领域API**，**多场景的应用示例**、和**高性能分布式训练**三大特点，旨在提升开发者在文本领域的开发效率，并提供丰富的NLP应用示例。
2323

2424
- **易用的文本领域API**
25-
- 提供丰富的工业级预置任务能力[Taskflow](./docs/model_zoo/taskflow.md)和全流程的文本领域API：支持丰富中文数据集加载的[Dataset API](https://paddlenlp.readthedocs.io/zh/latest/data_prepare/dataset_list.html)；灵活高效地完成数据预处理的[Data API](https://paddlenlp.readthedocs.io/zh/latest/source/paddlenlp.data.html)；提供60+预训练模型的[Transformer API](./docs/model_zoo/transformers.rst)等，可大幅提升NLP任务建模的效率。
25+
- 提供丰富的产业级预置任务能力[Taskflow](./docs/model_zoo/taskflow.md)和全流程的文本领域API：支持丰富中文数据集加载的[Dataset API](https://paddlenlp.readthedocs.io/zh/latest/data_prepare/dataset_list.html)；灵活高效地完成数据预处理的[Data API](https://paddlenlp.readthedocs.io/zh/latest/source/paddlenlp.data.html)；提供60+预训练模型的[Transformer API](./docs/model_zoo/transformers.rst)等，可大幅提升NLP任务建模的效率。
2626

2727
- **多场景的应用示例**
28-
- 覆盖从学术到工业级的NLP[应用示例](#多场景的应用示例)，涵盖NLP基础技术、NLP核心技术、NLP系统应用以及相关拓展应用。全面基于飞桨核心框架2.0全新API体系开发，为开发提供飞桨框架在文本领域的最佳实践。
28+
- 覆盖从学术到工业级的NLP[应用示例](#多场景的应用示例)，涵盖NLP基础技术、NLP核心技术、NLP系统应用以及相关拓展应用。全面基于飞桨核心框架2.0全新API体系开发，为开发者提供飞桨文本领域的最佳实践。
2929

3030
- **高性能分布式训练**
3131
- 基于飞桨核心框架领先的自动混合精度优化策略，结合分布式Fleet API，支持4D混合并行策略，可高效地完成超大规模参数的模型训练。
@@ -275,7 +275,6 @@ PaddleNLP提供了多粒度、多场景的NLP应用示例，面向动态图模
275275
| [OFA-BERT](./examples/model_compression/ofa/) :star2: | 基于PaddleSlim Once-For-ALL(OFA)策略对BERT在GLUE任务的下游模型进行压缩，在精度无损的情况下可减少33%参数量，达到模型小型化的提速的效果。 |
276276
| [Distill-LSTM](./examples/model_compression/distill_lstm/) | 基于[Distilling Task-Specific Knowledge from BERT into Simple Neural Networks](https://arxiv.org/abs/1903.12136)论文策略的实现，将BERT中英文分类的下游模型知识通过蒸馏的方式迁移至LSTM的小模型结构中，取得比LSTM单独训练更好的效果。 |
277277

278-
279278
#### 小样本学习 (Few-Shot Learning)
280279

281280
| 算法 | 简介 |
@@ -284,8 +283,6 @@ PaddleNLP提供了多粒度、多场景的NLP应用示例，面向动态图模
284283
| [P-Tuning](./examples/few_shot/p-tuning/) |基于[GPT Understands, Too](https://arxiv.org/pdf/2103.10385.pdf) 论文策略实现, 首次提出连续可学习的模板参数，在全参数空间对模板进行连续优化，大幅提升模型稳定性和模型效果。|
285284
| [EFL](./examples/few_shot/efl/) | 基于[Entailment as Few-Shot Learner](https://arxiv.org/abs/2104.14690) 论文策略实现，将下游目标任务转换为蕴含任务降低模型预测空间，显著提升模型效果。|
286285

287-
288-
289286
## 交互式Notebook教程
290287

291288
- [使用Seq2Vec模块进行句子情感分类](https://aistudio.baidu.com/aistudio/projectdetail/1283423)
@@ -298,7 +295,6 @@ PaddleNLP提供了多粒度、多场景的NLP应用示例，面向动态图模
298295

299296
更多教程参见[PaddleNLP on AI Studio](https://aistudio.baidu.com/aistudio/personalcenter/thirdview/574995)。
300297

301-
302298
## 社区贡献与技术交流
303299

304300
### 特殊兴趣小组
@@ -313,7 +309,6 @@ PaddleNLP提供了多粒度、多场景的NLP应用示例，面向动态图模
313309
<img src="./docs/imgs/qq.png" width="200" height="200" />
314310
</div>
315311

316-
317312
## 版本更新
318313

319314
更多版本更新说明请查看[ChangeLog](./docs/changelog.md)

‎README_en.md‎

Lines changed: 47 additions & 18 deletions
Original file line numberDiff line numberDiff line change
@@ -14,9 +14,7 @@ English | [简体中文](./README.md)
1414

1515
## News <img src="./docs/imgs/news_icon.png" width="40"/>
1616

17-
* [2021-06-07] **NLP Live Course** from Baidu has started!🔥🔥🔥 Click [HERE](https://aistudio.baidu.com/aistudio/course/introduce/24177) to join us!
18-
* [2021-06-04] [ERNIE-Gram](https://arxiv.org/abs/2010.12148) pretrained model has been released! Install v2.0.2 to try it.
19-
* [2021-05-20] PaddleNLP 2.0 has been officially relealsed! :tada: For more information please refer to [Release Note](https://github.com/PaddlePaddle/PaddleNLP/releases/tag/v2.0.0).
17+
* [2021-10-12] PaddleNLP 2.1 has been officially relealsed! :tada: For more information please refer to [Release Note](https://github.com/PaddlePaddle/PaddleNLP/releases/tag/v2.1.0).
2018

2119
## Introduction
2220

@@ -41,17 +39,52 @@ English | [简体中文](./README.md)
4139

4240
More information about PaddlePaddle installation please refer to [PaddlePaddle's Website](https://www.paddlepaddle.org.cn/install/quick?docurl=/documentation/docs/zh/install/conda/linux-conda.html).
4341

44-
### PIP Installation
42+
### Python pip Installation
4543

4644
```
4745
pip install --upgrade paddlenlp
4846
```
4947

5048
## Easy-to-use API
5149

50+
### Taskflow：Off-the-shelf Industial NLP Pre-built Task
51+
52+
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.
53+
54+
```python
55+
from paddlenlp import Taskflow
56+
57+
# Chinese Word Segmentation
58+
seg = Taskflow("word_segmentation")
59+
seg("第十四届全运会在西安举办")
60+
>>> ['第十四届', '全运会', '在', '西安', '举办']
61+
62+
# POS Tagging
63+
tag = Taskflow("pos_tagging")
64+
tag("第十四届全运会在西安举办")
65+
>>> [('第十四届', 'm'), ('全运会', 'nz'), ('在', 'p'), ('西安', 'LOC'), ('举办', 'v')]
66+
67+
# Named Entity Recognition
68+
ner = Taskflow("ner")
69+
ner("《孤女》是2010年九州出版社出版的小说，作者是余兼羽")
70+
>>> [('《', 'w'), ('孤女', '作品类_实体'), ('》', 'w'), ('是', '肯定词'), ('2010年', '时间类'), ('九州出版社', '组织机构类'), ('出版', '场景事件'), ('的', '助词'), ('小说', '作品类_概念'), ('，', 'w'), ('作者', '人物类_概念'), ('是', '肯定词'), ('余兼羽', '人物类_实体')]
71+
72+
# Dependency Parsing
73+
ddp = Taskflow("dependency_parsing")
74+
ddp("百度是一家高科技公司")
75+
>>> [{'word': ['百度', '是', '一家', '高科技', '公司'], 'head': ['2', '0', '5', '5', '2'], 'deprel': ['SBV', 'HED', 'ATT', 'ATT', 'VOB']}]
76+
77+
# Sentiment Analysis
78+
senta = Taskflow("sentiment_analysis")
79+
senta("怀着十分激动的心情放映，可是看着看着发现，在放映完毕后，出现一集米老鼠的动画片")
80+
>>> [{'text': '怀着十分激动的心情放映，可是看着看着发现，在放映完毕后，出现一集米老鼠的动画片', 'label': 'negative'}]
81+
```
82+
83+
For more usage please refer to [Taskflow Docs](./docs/model_zoo/taskflow.md)
84+
5285
### Transformer API: Awesome Pre-trained Model Ecosystem
5386

54-
We provide **15** network architectures and **67** pretrained models. Not only includes all the SOTA model like ERNIE, PLATO and SKEP released by Baidu, but also integrates most of the high quality Chinese pretrained model developed by other organizations. We also welcome developer to contribute your Transformer models! 🤗
87+
We provide **22** network architectures and over **90** pretrained models. Not only includes all the SOTA model like ERNIE, PLATO and SKEP released by Baidu, but also integrates most of the high quality Chinese pretrained model developed by other organizations. We welcome all developers to contribute your Transformer models to PaddleNLP! 🤗
5588

5689
```python
5790
from paddlenlp.transformers import *
@@ -87,8 +120,7 @@ model = ErnieForQuestionAnswering.from_pretrained('ernie-1.0')
87120

88121
For more pretrained model usage, please refer to [Transformer API](./docs/model_zoo/transformers.rst)
89122

90-
91-
### Dataset API: Rich Dataset Integration and Quick Loading
123+
### Dataset API: Abundant Dataset Integration and Quick Loading
92124

93125
```python
94126
from paddlenlp.datasets import load_dataset
@@ -124,36 +156,33 @@ Please find more API Reference from our [readthedocs](https://paddlenlp.readthed
124156

125157
## Wide-range NLP Task Support
126158

127-
PaddleNLP provide rich application examples covers mainstream NLP task to help developer accelerate problem solving.
159+
PaddleNLP provides rich application examples covering mainstream NLP task to help developers accelerate problem solving.
128160

129-
### NLP Basic Task
161+
### NLP Basic Technique
130162

131163
- [Word Embedding](./examples/word_embedding/)
132164
- [Lexical Analysis](./examples/lexical_analysis/)
133165
- [Language Model](./examples/language_model/)
134166
- [Semantic Parsing (Text to SQL)](./examples/text_to_sql):star:
135-
136-
137-
### NLP Core Technique
138-
139167
- [Text Classification](./examples/text_classification/)
140168
- [Text Matching](./examples/text_matching/)
141169
- [Text Generation](./examples/text_generation/)
170+
- [Text Correction](./examples/text_correction/):star:
142171
- [Semantic Indexing](./examples/semantic_indexing/)
143172
- [Information Extraction](./examples/information_extraction/)
144173

145-
### NLP Industrial Applications
174+
### NLP System
146175

147-
- [Sentiment Analysis](./examples/sentiment_analysis/skep/):star2:
176+
- [Sentiment Analysis](./examples/sentiment_analysis/):star2:
148177
- [General Dialogue System](./examples/dialogue/)
149178
- [Machine Translation](./examples/machine_translation/)
150179
- [Simultaneous Translation](././examples/simultaneous_translation/)
151180
- [Machine Reading Comprehension](./examples/machine_reading_comprehension/)
152181

153-
### Extented Application
182+
### NLP Extented Applications
154183

155-
- [Text Knowledge Linking](./examples/text_to_knowledge/):star2:
156-
- [Machine Reading Comprehension](./examples/machine_reading_comprehension)
184+
- [Few-shot Learning](./examples/few_shot/):star2:
185+
- [Text Knowledge Mining](./examples/text_to_knowledge/):star2:
157186
- [Model Compression](./examples/model_compression/)
158187
- [Text Graph Learning](./examples/text_graph/erniesage/)
159188
- [Time Series Prediction](./examples/time_series/)

‎docs/model_zoo/taskflow.md‎

Lines changed: 16 additions & 13 deletions
Original file line numberDiff line numberDiff line change
@@ -1,20 +1,23 @@
11
# PaddleNLP Taskflow
22

3-
- [介绍](#介绍)
4-
* [任务清单](#任务清单)
5-
- [用法](#用法)
6-
* [中文分词](#中文分词)
7-
* [词性标注](#词性标注)
8-
* [命名实体识别](#命名实体识别)
9-
* [文本纠错](#文本纠错)
10-
* [句法分析](#句法分析)
11-
* [情感分析](#情感分析)
12-
* [生成式问答](#生成式问答)
13-
* [智能写诗](#智能写诗)
3+
- [PaddleNLP Taskflow](#paddlenlp-taskflow)
4+
- [介绍](#介绍)
5+
- [任务清单](#任务清单)
6+
- [用法](#用法)
7+
- [查看使用示例](#查看使用示例)
8+
- [中文分词](#中文分词)
9+
- [词性标注](#词性标注)
10+
- [命名实体识别](#命名实体识别)
11+
- [文本纠错](#文本纠错)
12+
- [句法分析](#句法分析)
13+
- [情感分析](#情感分析)
14+
- [知识挖掘](#知识挖掘)
15+
- [生成式问答](#生成式问答)
16+
- [智能写诗](#智能写诗)
1417

1518
## 介绍
1619

17-
`paddlenlp.Taskflow`是功能强大的自然语言处理库，旨在提供开箱即用的NLP预置任务，覆盖自然语言理解与自然语言生成两大核心应用，在中文场景上提供工业级的效果与极致的预测性能。
20+
`paddlenlp.Taskflow`是旨在提供开箱即用的NLP预置任务，覆盖自然语言理解与自然语言生成两大核心应用，在中文场景上提供产业级的效果与极致的预测性能。
1821

1922
### 任务清单
2023

@@ -27,7 +30,7 @@
2730
| 句法分析 | 自动对联(TODO) |
2831
| 情感分析 | |
2932

30-
随着版本迭代后续会持续开放更多的应用场景。
33+
随着版本迭代会持续开放更多的应用场景。
3134

3235
## 用法
3336

0 commit comments

Comments
 (0)