From a82be5a95eb2f6470a337f142ea562b9c0df033b Mon Sep 17 00:00:00 2001
From: Vu Anh <anhv.ict91@gmail.com>
Date: Fri, 25 Dec 2020 12:03:28 +0700
Subject: [PATCH] GH-351: Release v1.3.1a0 (#377)

---
 HISTORY.rst         |   5 +
 README.md           | 272 +++++++++++++++++++++++++++++++++++++++++
 README.rst          | 291 -------------------------------------------
 docs/readme.rst     | 292 +++++++++++++++++++++++++++++++++++++++++++-
 logo.png            | Bin 0 -> 11393 bytes
 setup.py            |   7 +-
 underthesea/VERSION |   2 +-
 7 files changed, 571 insertions(+), 298 deletions(-)
 create mode 100644 README.md
 delete mode 100644 README.rst
 create mode 100644 logo.png

diff --git a/HISTORY.rst b/HISTORY.rst
index d0197039..fb6eed5e 100644
--- a/HISTORY.rst
+++ b/HISTORY.rst
@@ -2,6 +2,11 @@
 History
 ================================================================================
 
+Current
+--------------------------------------------------------------------------------
+
+* [Funny Update] Change underthesea's avatar (GH-371)
+
 1.3.0 (2020-12-11)
 --------------------------------------------------------------------------------
 
diff --git a/README.md b/README.md
new file mode 100644
index 00000000..95372628
--- /dev/null
+++ b/README.md
@@ -0,0 +1,272 @@
+<p align="center">
+  <br>
+  <img src="logo.png"/>
+  <br/>
+</p>
+
+<p align="center">
+  <a href="https://pypi.python.org/pypi/underthesea">
+    <img src="https://img.shields.io/pypi/v/underthesea.svg">
+  </a>
+  <a href="https://pypi.python.org/pypi/underthesea">
+    <img src="https://img.shields.io/pypi/pyversions/underthesea.svg">
+  </a>
+  <a href="https://travis-ci.org/undertheseanlp/underthesea">
+    <img src="https://img.shields.io/travis/undertheseanlp/underthesea.svg">
+  </a>
+  <a href="http://underthesea.readthedocs.io/en/latest/">
+    <img src="https://readthedocs.org/projects/underthesea/badge/?version=latest">
+  </a>
+  <a href="http://undertheseanlp.com/">
+    <img src="https://img.shields.io/badge/website-online-brightgreen">
+  </a>
+  <a href="https://colab.research.google.com/drive/1gD8dSMSE_uNacW4qJ-NSnvRT85xo9ZY2">
+    <img src="https://img.shields.io/badge/colab-latest-ff9f01">
+  </a>
+  <a href="https://colab.research.google.com/drive/1U6EWY7ewNUtCXGsa5uZtDEz4I5exO_fo">
+    <img src="https://img.shields.io/badge/colab-stable-ff9f01">
+  </a>
+  <a href="https://www.facebook.com/undertheseanlp/">
+    <img src="https://img.shields.io/badge/Facebook-1877F2?logo=facebook&logoColor=white">
+  </a>
+  <a href="https://www.youtube.com/channel/UC9Jv1Qg49uprg6SjkyAqs9A">
+    <img src="https://img.shields.io/badge/YouTube-FF0000?logo=youtube&logoColor=white">
+  </a>
+</p>
+
+<h3 align="center">
+Open-source Vietnamese Natural Language Process Toolkit
+</h3>
+
+`Underthesea` is:
+
+🌊 **A Vietnamese NLP toolkit.** Underthesea is a suite of open source Python modules data sets and tutorials supporting research and development in [Vietnamese Natural Language Processing](https://github.com/undertheseanlp/underthesea). We provides extremely easy API to quickly apply pretrained NLP models to your Vietnamese text, such as word segmentation, part-of-speech tagging (PoS), named entity recognition (NER), text classification and dependency parsing.
+
+🌊 **A Pytorch library.** Underthesea is backed by one of most popular deep learning libraries, [Pytorch](https://pytorch.org/), make it easy to train your deep learning models and experiment with new approaches using Underthesea modules and classes.
+
+🌊 **An open-source software.** Underthesea is published under the [GNU General Public License v3.0](https://github.com/undertheseanlp/underthesea/blob/master/LICENSE) license. Permissions of this strong copyleft license are conditioned on making available complete source code of licensed works and modifications, which include larger works using a licensed work, under the same license.
+
+💫 **Version 1.3.0 out now!** [Underthesea meet deep learning!](https://github.com/undertheseanlp/underthesea/issues/359)
+
+## Installation
+
+
+To install underthesea, simply:
+
+```bash
+$ pip install underthesea
+✨🍰✨
+```
+
+Satisfaction, guaranteed.
+
+## Tutorials
+
+* [1. Sentence Segmentation](#1-sentence-segmentation)
+* [2. Word Segmentation](#2-word-segmentation)
+* [3. POS Tagging](#3-pos-tagging)
+* [4. Chunking](#4-chunking)
+* [5. Dependency Parsing](#5-dependency-parsing)
+* [6. Named Entity Recognition](#6-named-entity-recognition)
+* [7. Text Classification](#7-text-classification)
+* [8. Sentiment Analysis](#8-sentiment-analysis)
+* [9. Vietnamese NLP Resources](#9-vietnamese-nlp-resources)
+
+### 1. Sentence Segmentation
+
+Usage
+
+```python
+>>> from underthesea import sent_tokenize
+>>> text = 'Taylor cho biết lúc đầu cô cảm thấy ngại với cô bạn thân Amanda nhưng rồi mọi thứ trôi qua nhanh chóng. Amanda cũng thoải mái với mối quan hệ này.'
+
+>>> sent_tokenize(text)
+[
+  "Taylor cho biết lúc đầu cô cảm thấy ngại với cô bạn thân Amanda nhưng rồi mọi thứ trôi qua nhanh chóng.",
+  "Amanda cũng thoải mái với mối quan hệ này."
+]
+```
+
+### 2. Word Segmentation
+
+Usage
+
+```python
+>>> from underthesea import word_tokenize
+>>> sentence = 'Chàng trai 9X Quảng Trị khởi nghiệp từ nấm sò'
+
+>>> word_tokenize(sentence)
+['Chàng trai', '9X', 'Quảng Trị', 'khởi nghiệp', 'từ', 'nấm', 'sò']
+
+>>> word_tokenize(sentence, format="text")
+'Chàng_trai 9X Quảng_Trị khởi_nghiệp từ nấm sò'
+```
+
+### 3. POS Tagging
+
+
+Usage
+
+```python
+>>> from underthesea import pos_tag
+>>> pos_tag('Chợ thịt chó nổi tiếng ở Sài Gòn bị truy quét')
+[('Chợ', 'N'),
+ ('thịt', 'N'),
+ ('chó', 'N'),
+ ('nổi tiếng', 'A'),
+ ('ở', 'E'),
+ ('Sài Gòn', 'Np'),
+ ('bị', 'V'),
+ ('truy quét', 'V')]
+```
+
+
+### 4. Chunking
+
+
+Usage
+
+```python
+>>> from underthesea import chunk
+>>> text = 'Bác sĩ bây giờ có thể thản nhiên báo tin bệnh nhân bị ung thư?'
+>>> chunk(text)
+[('Bác sĩ', 'N', 'B-NP'),
+ ('bây giờ', 'P', 'I-NP'),
+ ('có thể', 'R', 'B-VP'),
+ ('thản nhiên', 'V', 'I-VP'),
+ ('báo tin', 'N', 'B-NP'),
+ ('bệnh nhân', 'N', 'I-NP'),
+ ('bị', 'V', 'B-VP'),
+ ('ung thư', 'N', 'I-VP'),
+ ('?', 'CH', 'O')]
+```
+
+
+### 5. Dependency Parsing
+
+
+Usage
+
+```python
+>>> from underthesea import dependency_parse
+>>> text = 'Tối 29/11, Việt Nam thêm 2 ca mắc Covid-19'
+>>> dependency_parse(text)
+[('Tối', 5, 'obl:tmod'),
+ ('29/11', 1, 'flat:date'),
+ (',', 1, 'punct'),
+ ('Việt Nam', 5, 'nsubj'),
+ ('thêm', 0, 'root'),
+ ('2', 7, 'nummod'),
+ ('ca', 5, 'obj'),
+ ('mắc', 7, 'nmod'),
+ ('Covid-19', 8, 'nummod')]
+```
+
+
+### 6. Named Entity Recognition
+
+
+Usage
+
+```python
+>>> from underthesea import ner
+>>> text = 'Chưa tiết lộ lịch trình tới Việt Nam của Tổng thống Mỹ Donald Trump'
+>>> ner(text)
+[('Chưa', 'R', 'O', 'O'),
+ ('tiết lộ', 'V', 'B-VP', 'O'),
+ ('lịch trình', 'V', 'B-VP', 'O'),
+ ('tới', 'E', 'B-PP', 'O'),
+ ('Việt Nam', 'Np', 'B-NP', 'B-LOC'),
+ ('của', 'E', 'B-PP', 'O'),
+ ('Tổng thống', 'N', 'B-NP', 'O'),
+ ('Mỹ', 'Np', 'B-NP', 'B-LOC'),
+ ('Donald', 'Np', 'B-NP', 'B-PER'),
+ ('Trump', 'Np', 'B-NP', 'I-PER')]
+```
+
+### 7. Text Classification
+
+
+Download models
+
+```bash
+$ underthesea download-model TC_GENERAL
+$ underthesea download-model TC_BANK
+```
+
+Usage
+
+```python
+>>> from underthesea import classify
+
+>>> classify('HLV đầu tiên ở Premier League bị sa thải sau 4 vòng đấu')
+['The thao']
+
+>>> classify('Hội đồng tư vấn kinh doanh Asean vinh danh giải thưởng quốc tế')
+['Kinh doanh']
+
+>> classify('Lãi suất từ BIDV rất ưu đãi', domain='bank')
+['INTEREST_RATE']
+```
+
+
+### 8. Sentiment Analysis
+
+Download models
+
+```bash
+$ underthesea download-model SA_GENERAL
+$ underthesea download-model SA_BANK
+```
+
+Usage
+
+
+```python
+>>> from underthesea import sentiment
+
+>>> sentiment('hàng kém chất lg,chăn đắp lên dính lông lá khắp người. thất vọng')
+negative
+>>> sentiment('Sản phẩm hơi nhỏ so với tưởng tượng nhưng chất lượng tốt, đóng gói cẩn thận.')
+positive
+
+>>> sentiment('Đky qua đường link ở bài viết này từ thứ 6 mà giờ chưa thấy ai lhe hết', domain='bank')
+['CUSTOMER_SUPPORT#negative']
+>>> sentiment('Xem lại vẫn thấy xúc động và tự hào về BIDV của mình', domain='bank')
+['TRADEMARK#positive']
+```
+
+### 9. Vietnamese NLP Resources
+
+List resources
+
+```bash
+$ underthesea list-data
+| Name         | Type        | License   |   Year | Directory             |
+|--------------+-------------+-----------+--------+-----------------------|
+| UTS2017-BANK | Categorized | Open      |   2017 | datasets/UTS2017-BANK |
+| VNESES       | Plaintext   | Open      |   2012 | datasets/LTA          |
+| VNTQ_BIG     | Plaintext   | Open      |   2012 | datasets/LTA          |
+| VNTQ_SMALL   | Plaintext   | Open      |   2012 | datasets/LTA          |
+| VNTC         | Categorized | Open      |   2007 | datasets/VNTC         |
+
+$ underthesea list-data --all
+```
+
+Download resources
+
+```bash
+$ underthesea download-data VNTC
+100%|██████████| 74846806/74846806 [00:09<00:00, 8243779.16B/s]
+Resource VNTC is downloaded in ~/.underthesea/datasets/VNTC folder
+```
+
+### Up Coming Features
+
+* Machine Translation
+* Text to Speech
+* Automatic Speech Recognition
+
+### Contributing
+
+Do you want to contribute with underthesea development? Great! Please read more details at [CONTRIBUTING.rst](https://github.com/undertheseanlp/underthesea/blob/master/CONTRIBUTING.rst)
diff --git a/README.rst b/README.rst
deleted file mode 100644
index 73de28f7..00000000
--- a/README.rst
+++ /dev/null
@@ -1,291 +0,0 @@
-====================================
-Underthesea - Vietnamese NLP Toolkit
-====================================
-
-
-.. image:: https://img.shields.io/pypi/v/underthesea.svg
-        :target: https://pypi.python.org/pypi/underthesea
-
-.. image:: https://img.shields.io/pypi/pyversions/underthesea.svg
-        :target: https://pypi.python.org/pypi/underthesea
-
-.. image:: https://img.shields.io/badge/license-GNU%20General%20Public%20License%20v3-brightgreen.svg
-        :target: https://pypi.python.org/pypi/underthesea
-
-.. image:: https://img.shields.io/travis/undertheseanlp/underthesea.svg
-        :target: https://travis-ci.org/undertheseanlp/underthesea
-
-.. image:: https://readthedocs.org/projects/underthesea/badge/?version=latest
-        :target: http://underthesea.readthedocs.io/en/latest/
-        :alt: Documentation Status
-
-.. image:: https://img.shields.io/badge/chat-on%20facebook-green.svg
-    :target: https://www.facebook.com/undertheseanlp/
-
-|
-
-.. image:: https://raw.githubusercontent.com/undertheseanlp/underthesea/master/logo.jpg
-        :target: https://raw.githubusercontent.com/undertheseanlp/underthesea/master/logo.jpg
-
-**underthesea** is a suite of open source Python modules, data sets and tutorials supporting research and development in Vietnamese Natural Language Processing.
-
-💫 **Version 1.3.0 out now!** `Underthesea meet deep learning! <https://github.com/undertheseanlp/underthesea/issues/359>`_
-
-+-----------------+------------------------------------------------------------------------------------------------+
-| Free software   | GNU General Public License v3                                                                  |
-+-----------------+------------------------------------------------------------------------------------------------+
-| Live demo       | `undertheseanlp.com <http://undertheseanlp.com/>`_                                             |
-+-----------------+------------------------------------------------------------------------------------------------+
-| Colab notebooks | `latest <https://colab.research.google.com/drive/1gD8dSMSE_uNacW4qJ-NSnvRT85xo9ZY2>`_          |
-|                 | /                                                                                              |
-|                 | `stable <https://colab.research.google.com/drive/1U6EWY7ewNUtCXGsa5uZtDEz4I5exO_fo>`_          |
-+-----------------+------------------------------------------------------------------------------------------------+
-| Documentation   | `Underthesea Documentation <http://underthesea.readthedocs.io/en/latest/>`_                    |
-+-----------------+------------------------------------------------------------------------------------------------+
-| Facebook        | `Underthesea Page <https://www.facebook.com/undertheseanlp/>`_                                 |
-+-----------------+------------------------------------------------------------------------------------------------+
-| Youtube         | `Underthesea NLP Channel <https://www.youtube.com/channel/UC9Jv1Qg49uprg6SjkyAqs9A>`_          |
-+-----------------+------------------------------------------------------------------------------------------------+
-
-Installation
-----------------------------------------
-
-To install underthesea, simply:
-
-.. code-block:: bash
-
-    $ pip install underthesea
-    ✨🍰✨
-
-Satisfaction, guaranteed.
-
-Usage
-----------------------------------------
-
-* `1. Sentence Segmentation <#1-sentence-segmentation>`_
-* `2. Word Segmentation <#2-word-segmentation>`_
-* `3. POS Tagging <#3-pos-tagging>`_
-* `4. Chunking <#4-chunking>`_
-* `5. Dependency Parsing <#5-dependency-parsing>`_
-* `6. Named Entity Recognition <#6-named-entity-recognition>`_
-* `7. Text Classification <#7-text-classification>`_
-* `8. Sentiment Analysis <#8-sentiment-analysis>`_
-* `9. Vietnamese NLP Resources <#9-vietnamese-nlp-resources>`_
-
-****************************************
-1. Sentence Segmentation
-****************************************
-
-Usage
-
-.. code-block:: python
-
-    >>> # -*- coding: utf-8 -*-
-    >>> from underthesea import sent_tokenize
-    >>> text = 'Taylor cho biết lúc đầu cô cảm thấy ngại với cô bạn thân Amanda nhưng rồi mọi thứ trôi qua nhanh chóng. Amanda cũng thoải mái với mối quan hệ này.'
-
-    >>> sent_tokenize(text)
-    [
-        "Taylor cho biết lúc đầu cô cảm thấy ngại với cô bạn thân Amanda nhưng rồi mọi thứ trôi qua nhanh chóng.",
-        "Amanda cũng thoải mái với mối quan hệ này."
-    ]
-
-****************************************
-2. Word Segmentation
-****************************************
-
-Usage
-
-.. code-block:: python
-
-    >>> # -*- coding: utf-8 -*-
-    >>> from underthesea import word_tokenize
-    >>> sentence = 'Chàng trai 9X Quảng Trị khởi nghiệp từ nấm sò'
-
-    >>> word_tokenize(sentence)
-    ['Chàng trai', '9X', 'Quảng Trị', 'khởi nghiệp', 'từ', 'nấm', 'sò']
-
-    >>> word_tokenize(sentence, format="text")
-    'Chàng_trai 9X Quảng_Trị khởi_nghiệp từ nấm sò'
-
-****************************************
-3. POS Tagging
-****************************************
-
-Usage
-
-.. code-block:: python
-
-    >>> # -*- coding: utf-8 -*-
-    >>> from underthesea import pos_tag
-    >>> pos_tag('Chợ thịt chó nổi tiếng ở Sài Gòn bị truy quét')
-    [('Chợ', 'N'),
-     ('thịt', 'N'),
-     ('chó', 'N'),
-     ('nổi tiếng', 'A'),
-     ('ở', 'E'),
-     ('Sài Gòn', 'Np'),
-     ('bị', 'V'),
-     ('truy quét', 'V')]
-
-****************************************
-4. Chunking
-****************************************
-
-Usage
-
-.. code-block:: python
-
-    >>> # -*- coding: utf-8 -*-
-    >>> from underthesea import chunk
-    >>> text = 'Bác sĩ bây giờ có thể thản nhiên báo tin bệnh nhân bị ung thư?'
-    >>> chunk(text)
-    [('Bác sĩ', 'N', 'B-NP'),
-     ('bây giờ', 'P', 'I-NP'),
-     ('có thể', 'R', 'B-VP'),
-     ('thản nhiên', 'V', 'I-VP'),
-     ('báo tin', 'N', 'B-NP'),
-     ('bệnh nhân', 'N', 'I-NP'),
-     ('bị', 'V', 'B-VP'),
-     ('ung thư', 'N', 'I-VP'),
-     ('?', 'CH', 'O')]
-
-****************************************
-5. Dependency Parsing
-****************************************
-
-Usage
-
-.. code-block:: python
-
-    >>> # -*- coding: utf-8 -*-
-    >>> from underthesea import dependency_parse
-    >>> text = 'Tối 29/11, Việt Nam thêm 2 ca mắc Covid-19'
-    >>> dependency_parse(text)
-    [('Tối', 5, 'obl:tmod'),
-     ('29/11', 1, 'flat:date'),
-     (',', 1, 'punct'),
-     ('Việt Nam', 5, 'nsubj'),
-     ('thêm', 0, 'root'),
-     ('2', 7, 'nummod'),
-     ('ca', 5, 'obj'),
-     ('mắc', 7, 'nmod'),
-     ('Covid-19', 8, 'nummod')]
-
-****************************************
-6. Named Entity Recognition
-****************************************
-
-Usage
-
-.. code-block:: python
-
-    >>> # -*- coding: utf-8 -*-
-    >>> from underthesea import ner
-    >>> text = 'Chưa tiết lộ lịch trình tới Việt Nam của Tổng thống Mỹ Donald Trump'
-    >>> ner(text)
-    [('Chưa', 'R', 'O', 'O'),
-     ('tiết lộ', 'V', 'B-VP', 'O'),
-     ('lịch trình', 'V', 'B-VP', 'O'),
-     ('tới', 'E', 'B-PP', 'O'),
-     ('Việt Nam', 'Np', 'B-NP', 'B-LOC'),
-     ('của', 'E', 'B-PP', 'O'),
-     ('Tổng thống', 'N', 'B-NP', 'O'),
-     ('Mỹ', 'Np', 'B-NP', 'B-LOC'),
-     ('Donald', 'Np', 'B-NP', 'B-PER'),
-     ('Trump', 'Np', 'B-NP', 'I-PER')]
-
-****************************************
-7. Text Classification
-****************************************
-
-Download models
-
-.. code-block:: bash
-
-    $ underthesea download-model TC_GENERAL
-    $ underthesea download-model TC_BANK
-
-Usage
-
-.. code-block:: python
-
-    >>> # -*- coding: utf-8 -*-
-    >>> from underthesea import classify
-
-    >>> classify('HLV đầu tiên ở Premier League bị sa thải sau 4 vòng đấu')
-    ['The thao']
-    >>> classify('Hội đồng tư vấn kinh doanh Asean vinh danh giải thưởng quốc tế')
-    ['Kinh doanh']
-
-    >> classify('Lãi suất từ BIDV rất ưu đãi', domain='bank')
-    ['INTEREST_RATE']
-
-****************************************
-8. Sentiment Analysis
-****************************************
-
-Download models
-
-.. code-block:: bash
-
-    $ underthesea download-model SA_GENERAL
-    $ underthesea download-model SA_BANK
-
-
-Usage
-
-
-.. code-block:: python
-
-    >>> # -*- coding: utf-8 -*-
-    >>> from underthesea import sentiment
-
-    >>> sentiment('hàng kém chất lg,chăn đắp lên dính lông lá khắp người. thất vọng')
-    negative
-    >>> sentiment('Sản phẩm hơi nhỏ so với tưởng tượng nhưng chất lượng tốt, đóng gói cẩn thận.')
-    positive
-
-    >>> sentiment('Đky qua đường link ở bài viết này từ thứ 6 mà giờ chưa thấy ai lhe hết', domain='bank')
-    ['CUSTOMER_SUPPORT#negative']
-    >>> sentiment('Xem lại vẫn thấy xúc động và tự hào về BIDV của mình', domain='bank')
-    ['TRADEMARK#positive']
-
-****************************************
-9. Vietnamese NLP Resources
-****************************************
-
-List resources
-
-.. code-block:: bash
-
-    $ underthesea list-data
-    | Name         | Type        | License   |   Year | Directory             |
-    |--------------+-------------+-----------+--------+-----------------------|
-    | UTS2017-BANK | Categorized | Open      |   2017 | datasets/UTS2017-BANK |
-    | VNESES       | Plaintext   | Open      |   2012 | datasets/LTA          |
-    | VNTQ_BIG     | Plaintext   | Open      |   2012 | datasets/LTA          |
-    | VNTQ_SMALL   | Plaintext   | Open      |   2012 | datasets/LTA          |
-    | VNTC         | Categorized | Open      |   2007 | datasets/VNTC         |
-
-    $ underthesea list-data --all
-
-Download resources
-
-.. code-block:: bash
-
-    $ underthesea download-data VNTC
-    100%|██████████| 74846806/74846806 [00:09<00:00, 8243779.16B/s]
-    Resource VNTC is downloaded in ~/.underthesea/datasets/VNTC folder
-
-Up Coming Features
-----------------------------------------
-
-* Machine Translation
-* Text to Speech
-* Automatic Speech Recognition
-
-Contributing
-----------------------------------------
-
-Do you want to contribute with underthesea development? Great! Please read more details at `CONTRIBUTING.rst. <https://github.com/undertheseanlp/underthesea/blob/master/CONTRIBUTING.rst>`_
diff --git a/docs/readme.rst b/docs/readme.rst
index de17838e..73de28f7 100644
--- a/docs/readme.rst
+++ b/docs/readme.rst
@@ -1 +1,291 @@
-.. include:: ../README.rst
+====================================
+Underthesea - Vietnamese NLP Toolkit
+====================================
+
+
+.. image:: https://img.shields.io/pypi/v/underthesea.svg
+        :target: https://pypi.python.org/pypi/underthesea
+
+.. image:: https://img.shields.io/pypi/pyversions/underthesea.svg
+        :target: https://pypi.python.org/pypi/underthesea
+
+.. image:: https://img.shields.io/badge/license-GNU%20General%20Public%20License%20v3-brightgreen.svg
+        :target: https://pypi.python.org/pypi/underthesea
+
+.. image:: https://img.shields.io/travis/undertheseanlp/underthesea.svg
+        :target: https://travis-ci.org/undertheseanlp/underthesea
+
+.. image:: https://readthedocs.org/projects/underthesea/badge/?version=latest
+        :target: http://underthesea.readthedocs.io/en/latest/
+        :alt: Documentation Status
+
+.. image:: https://img.shields.io/badge/chat-on%20facebook-green.svg
+    :target: https://www.facebook.com/undertheseanlp/
+
+|
+
+.. image:: https://raw.githubusercontent.com/undertheseanlp/underthesea/master/logo.jpg
+        :target: https://raw.githubusercontent.com/undertheseanlp/underthesea/master/logo.jpg
+
+**underthesea** is a suite of open source Python modules, data sets and tutorials supporting research and development in Vietnamese Natural Language Processing.
+
+💫 **Version 1.3.0 out now!** `Underthesea meet deep learning! <https://github.com/undertheseanlp/underthesea/issues/359>`_
+
++-----------------+------------------------------------------------------------------------------------------------+
+| Free software   | GNU General Public License v3                                                                  |
++-----------------+------------------------------------------------------------------------------------------------+
+| Live demo       | `undertheseanlp.com <http://undertheseanlp.com/>`_                                             |
++-----------------+------------------------------------------------------------------------------------------------+
+| Colab notebooks | `latest <https://colab.research.google.com/drive/1gD8dSMSE_uNacW4qJ-NSnvRT85xo9ZY2>`_          |
+|                 | /                                                                                              |
+|                 | `stable <https://colab.research.google.com/drive/1U6EWY7ewNUtCXGsa5uZtDEz4I5exO_fo>`_          |
++-----------------+------------------------------------------------------------------------------------------------+
+| Documentation   | `Underthesea Documentation <http://underthesea.readthedocs.io/en/latest/>`_                    |
++-----------------+------------------------------------------------------------------------------------------------+
+| Facebook        | `Underthesea Page <https://www.facebook.com/undertheseanlp/>`_                                 |
++-----------------+------------------------------------------------------------------------------------------------+
+| Youtube         | `Underthesea NLP Channel <https://www.youtube.com/channel/UC9Jv1Qg49uprg6SjkyAqs9A>`_          |
++-----------------+------------------------------------------------------------------------------------------------+
+
+Installation
+----------------------------------------
+
+To install underthesea, simply:
+
+.. code-block:: bash
+
+    $ pip install underthesea
+    ✨🍰✨
+
+Satisfaction, guaranteed.
+
+Usage
+----------------------------------------
+
+* `1. Sentence Segmentation <#1-sentence-segmentation>`_
+* `2. Word Segmentation <#2-word-segmentation>`_
+* `3. POS Tagging <#3-pos-tagging>`_
+* `4. Chunking <#4-chunking>`_
+* `5. Dependency Parsing <#5-dependency-parsing>`_
+* `6. Named Entity Recognition <#6-named-entity-recognition>`_
+* `7. Text Classification <#7-text-classification>`_
+* `8. Sentiment Analysis <#8-sentiment-analysis>`_
+* `9. Vietnamese NLP Resources <#9-vietnamese-nlp-resources>`_
+
+****************************************
+1. Sentence Segmentation
+****************************************
+
+Usage
+
+.. code-block:: python
+
+    >>> # -*- coding: utf-8 -*-
+    >>> from underthesea import sent_tokenize
+    >>> text = 'Taylor cho biết lúc đầu cô cảm thấy ngại với cô bạn thân Amanda nhưng rồi mọi thứ trôi qua nhanh chóng. Amanda cũng thoải mái với mối quan hệ này.'
+
+    >>> sent_tokenize(text)
+    [
+        "Taylor cho biết lúc đầu cô cảm thấy ngại với cô bạn thân Amanda nhưng rồi mọi thứ trôi qua nhanh chóng.",
+        "Amanda cũng thoải mái với mối quan hệ này."
+    ]
+
+****************************************
+2. Word Segmentation
+****************************************
+
+Usage
+
+.. code-block:: python
+
+    >>> # -*- coding: utf-8 -*-
+    >>> from underthesea import word_tokenize
+    >>> sentence = 'Chàng trai 9X Quảng Trị khởi nghiệp từ nấm sò'
+
+    >>> word_tokenize(sentence)
+    ['Chàng trai', '9X', 'Quảng Trị', 'khởi nghiệp', 'từ', 'nấm', 'sò']
+
+    >>> word_tokenize(sentence, format="text")
+    'Chàng_trai 9X Quảng_Trị khởi_nghiệp từ nấm sò'
+
+****************************************
+3. POS Tagging
+****************************************
+
+Usage
+
+.. code-block:: python
+
+    >>> # -*- coding: utf-8 -*-
+    >>> from underthesea import pos_tag
+    >>> pos_tag('Chợ thịt chó nổi tiếng ở Sài Gòn bị truy quét')
+    [('Chợ', 'N'),
+     ('thịt', 'N'),
+     ('chó', 'N'),
+     ('nổi tiếng', 'A'),
+     ('ở', 'E'),
+     ('Sài Gòn', 'Np'),
+     ('bị', 'V'),
+     ('truy quét', 'V')]
+
+****************************************
+4. Chunking
+****************************************
+
+Usage
+
+.. code-block:: python
+
+    >>> # -*- coding: utf-8 -*-
+    >>> from underthesea import chunk
+    >>> text = 'Bác sĩ bây giờ có thể thản nhiên báo tin bệnh nhân bị ung thư?'
+    >>> chunk(text)
+    [('Bác sĩ', 'N', 'B-NP'),
+     ('bây giờ', 'P', 'I-NP'),
+     ('có thể', 'R', 'B-VP'),
+     ('thản nhiên', 'V', 'I-VP'),
+     ('báo tin', 'N', 'B-NP'),
+     ('bệnh nhân', 'N', 'I-NP'),
+     ('bị', 'V', 'B-VP'),
+     ('ung thư', 'N', 'I-VP'),
+     ('?', 'CH', 'O')]
+
+****************************************
+5. Dependency Parsing
+****************************************
+
+Usage
+
+.. code-block:: python
+
+    >>> # -*- coding: utf-8 -*-
+    >>> from underthesea import dependency_parse
+    >>> text = 'Tối 29/11, Việt Nam thêm 2 ca mắc Covid-19'
+    >>> dependency_parse(text)
+    [('Tối', 5, 'obl:tmod'),
+     ('29/11', 1, 'flat:date'),
+     (',', 1, 'punct'),
+     ('Việt Nam', 5, 'nsubj'),
+     ('thêm', 0, 'root'),
+     ('2', 7, 'nummod'),
+     ('ca', 5, 'obj'),
+     ('mắc', 7, 'nmod'),
+     ('Covid-19', 8, 'nummod')]
+
+****************************************
+6. Named Entity Recognition
+****************************************
+
+Usage
+
+.. code-block:: python
+
+    >>> # -*- coding: utf-8 -*-
+    >>> from underthesea import ner
+    >>> text = 'Chưa tiết lộ lịch trình tới Việt Nam của Tổng thống Mỹ Donald Trump'
+    >>> ner(text)
+    [('Chưa', 'R', 'O', 'O'),
+     ('tiết lộ', 'V', 'B-VP', 'O'),
+     ('lịch trình', 'V', 'B-VP', 'O'),
+     ('tới', 'E', 'B-PP', 'O'),
+     ('Việt Nam', 'Np', 'B-NP', 'B-LOC'),
+     ('của', 'E', 'B-PP', 'O'),
+     ('Tổng thống', 'N', 'B-NP', 'O'),
+     ('Mỹ', 'Np', 'B-NP', 'B-LOC'),
+     ('Donald', 'Np', 'B-NP', 'B-PER'),
+     ('Trump', 'Np', 'B-NP', 'I-PER')]
+
+****************************************
+7. Text Classification
+****************************************
+
+Download models
+
+.. code-block:: bash
+
+    $ underthesea download-model TC_GENERAL
+    $ underthesea download-model TC_BANK
+
+Usage
+
+.. code-block:: python
+
+    >>> # -*- coding: utf-8 -*-
+    >>> from underthesea import classify
+
+    >>> classify('HLV đầu tiên ở Premier League bị sa thải sau 4 vòng đấu')
+    ['The thao']
+    >>> classify('Hội đồng tư vấn kinh doanh Asean vinh danh giải thưởng quốc tế')
+    ['Kinh doanh']
+
+    >> classify('Lãi suất từ BIDV rất ưu đãi', domain='bank')
+    ['INTEREST_RATE']
+
+****************************************
+8. Sentiment Analysis
+****************************************
+
+Download models
+
+.. code-block:: bash
+
+    $ underthesea download-model SA_GENERAL
+    $ underthesea download-model SA_BANK
+
+
+Usage
+
+
+.. code-block:: python
+
+    >>> # -*- coding: utf-8 -*-
+    >>> from underthesea import sentiment
+
+    >>> sentiment('hàng kém chất lg,chăn đắp lên dính lông lá khắp người. thất vọng')
+    negative
+    >>> sentiment('Sản phẩm hơi nhỏ so với tưởng tượng nhưng chất lượng tốt, đóng gói cẩn thận.')
+    positive
+
+    >>> sentiment('Đky qua đường link ở bài viết này từ thứ 6 mà giờ chưa thấy ai lhe hết', domain='bank')
+    ['CUSTOMER_SUPPORT#negative']
+    >>> sentiment('Xem lại vẫn thấy xúc động và tự hào về BIDV của mình', domain='bank')
+    ['TRADEMARK#positive']
+
+****************************************
+9. Vietnamese NLP Resources
+****************************************
+
+List resources
+
+.. code-block:: bash
+
+    $ underthesea list-data
+    | Name         | Type        | License   |   Year | Directory             |
+    |--------------+-------------+-----------+--------+-----------------------|
+    | UTS2017-BANK | Categorized | Open      |   2017 | datasets/UTS2017-BANK |
+    | VNESES       | Plaintext   | Open      |   2012 | datasets/LTA          |
+    | VNTQ_BIG     | Plaintext   | Open      |   2012 | datasets/LTA          |
+    | VNTQ_SMALL   | Plaintext   | Open      |   2012 | datasets/LTA          |
+    | VNTC         | Categorized | Open      |   2007 | datasets/VNTC         |
+
+    $ underthesea list-data --all
+
+Download resources
+
+.. code-block:: bash
+
+    $ underthesea download-data VNTC
+    100%|██████████| 74846806/74846806 [00:09<00:00, 8243779.16B/s]
+    Resource VNTC is downloaded in ~/.underthesea/datasets/VNTC folder
+
+Up Coming Features
+----------------------------------------
+
+* Machine Translation
+* Text to Speech
+* Automatic Speech Recognition
+
+Contributing
+----------------------------------------
+
+Do you want to contribute with underthesea development? Great! Please read more details at `CONTRIBUTING.rst. <https://github.com/undertheseanlp/underthesea/blob/master/CONTRIBUTING.rst>`_
diff --git a/logo.png b/logo.png
new file mode 100644
index 0000000000000000000000000000000000000000..90c04401322401f3de15769c3189fccaf2611cdf
GIT binary patch
literal 11393
zcmaiaWmKD8({2dvP@F=bP~4@sd(jpO1b3I>Qk+65P@paD6fI70D+HI|6t@7y9g5ot
z&-1?L{5aoQ-&(mN`_8@B-m_<}nYm^n->56%Vo_oN007+AN^+V201%A$u8)C+c(>$X
zen5PnnX4$u0hR%*fXdca=op9*Ocy0RcL0Es{^>&UDUkF+45E9yR+C5ngM)|9@B+4d
z7>XF8@Q??4$i8=SvU2tS$hujXd01J}dfR!}(ki}Id!rkIM+N}U0$$5Wzw?<t$n^E0
z(oJkwF_>D?=NL%(qrJ>(EYmkf_Ka5DT&7bBXn%o2GzvgQ#_8gfG9@<!^7%`3itH~y
z!;n5POomDcgv#zac1LE;s{5%K7&FZ2m)9ki+}^vEPAyeWeRo7mcqXACzND$GtGnV?
zx~sdD;TIbfk%tjV`}A6mU{L$#ODHW+g#bkw@j^-ZcL0O^>DT`-KnVW#+0g&~<G%xR
zRsZ~-0Oh{}L@H8grfzO7TEBqAIeVOTV@-QmK_$k%l>E%NH=Sf#m1Iv3tPatUmJP5}
zRG<nVp@(=|KD1x%+>B+#oU^fCMWKok*BZF2oM}v%{BpPW#lgY!wCs3fh-s!7$gkCS
zwL`@u$tK+GZpJ2LQ+D*Xfs`7+xBxy`Z_W~oR=cT?gZ^1i!f55deo#!wXRPV;6iq`P
z{IoB1Nmfv-GFyhi;nEwL>K9bCjod%M1e)L%;biZq@K_%l4feS-%ibO9V9Su!vdUw)
z@Gs*0#yM2|Xk+Zfdew%GZKPI*Zj`kt0gu}<T>ko9=V>otlhNQRb)t476Pl{kT)>^D
zl&jSnh*<tlOco5i?VMbWd>`JQSD6KkbD>qJb)*U4s9<0LAb}=j1DhS!Ck<8qghy9v
zJ#-^<uY)xQ)ki_!<Y}pLrfQ;;pkl7-)v5Y5lh7z_dD5O9QeqYieFDv&w7*e^E3ud>
zYKd!rSg=l%0Tz>YEWE5RGTlLMBAKQlmP_JBO2e1~RvlX*Z=n!R7p(w5<M?CL?H(tg
zO7hcDe}<;f-8l#Rs$LxoUNex767C@_=?|3-NvuI3){%N^ft*B1SMmER1*SbW8myJ|
znBP(^37w>(u+3BJzBR!*0zHnavGzy6@fl_K8Wy}9ik74G;U8V<MUU)AGeyW(ax&Dm
ze=W@%J4#!}F#L`IZcu&m?5o$0YVtv#f+fo-2e`>Hcg>TLROMqdS1q>;Tfqw_V*|tC
z1Li<OZ#!AKnz;MXnNs<!*J<ca3Q4Zf9r|h<x6H>*%2h3LkWg1g$IuET3HPOu?LkBZ
zN`^^1eU)3cc2+d^nT}OC*ejL<*4Yr|Yub_V(tqxw7hE@Woye8pNss8N3aO-fre0Xd
zX)73R=vRg&?VuQRENU{>#H0+$)n)g)StaN^Jl>mLO6#uWG*0BO(^n^Ss@si-k00K3
z7j8g<yDcyg^K=%!h*V(uDk-TWDfrVzZ5%U9yMMHU;2puSi3&1zCC+B@^A4+9>U;%A
z&gvWdeMz)mEGq{;t1AP!e{pIy9;EMa2~`)jIrgs_qxd6V{q9gZH`@_^+NzK*Vyn_+
zer0V!w$`{=qPFFO5dH83!na6?T!rkfzVz6mB!p%W*WyXFW3!bEwE?ehv5}7c^1law
z96l62Jhz*zJDxzpO#r?>KG#Plh&LvFvN%F;JQiwp75w1Et8Rv$w4VvJJE&Z(;yp35
z{#-(;u{IfLZJ!gO7lO@3)HzHc=+WY8v*9FI4@k4vjwltV##m+Xpr?7lw8oHlqh0*3
zyKZhw`_}?qL~A7J53y>$;eGjF&&}~MvCeQ#cu?7aNVTAM)rS|N$2q4L&Vu{eX?G`|
z-}^(F23KpDnbZf3Cmny%6-ve2xZlZnK1HEHc%5Z{UU~0a28$-;ma&P_9hLmog@!jo
zEaoxge{sHOWHiyGYr#gu(H>{nub!*CW&HIIF04m1V)R8m1~j&bVKe|6=AxRV0)gYw
zZ!L=Vfn(F@o8x36Z<aEL*z32|3a@uI8QTK(Hinq-VoUpF(sd1P%~d{@rX)|7E!IE+
z_ktP6j=q78$s2DNc;k;9dm`mIyBfbltmmD${8gFIj4y1jKm~DD4U{8(2jv$afO9%w
zy~6Wc`uQ?t*n%TCgYca*YfnfLUh{klrfpnFwK*x*&%)|flm$(ygKeAp`j3k(d8tfs
z=eLB13IPYgivx?P>o(x(;C!3!vHEQeyg9VE`LD8TiEr7}0BVC%e;>?b1A;1H%VB+-
zxEkd~^r8P4nVe~+v9t79B`JF?3A}kfrlHDaOPUhj8v?1z2B8K~XN{&+r@ph3S5Xn&
z%UXbCr-=x!*<sB3p1U3fUT~i|u!6<>(CR}I(3f7%u2`&<=nM~{RmXi=Chm?)#W^B*
z5zirEF<ea?WVJ`-ohyu^A<Z_1(|xF~`=|n6u5+OLKC$$VHvl@wG&vaE!$P>&<YUTd
zg}>5X7-leK&%p{ukTmO2lX`}u?Hm8xS<NyOIQsrby%jiGg&ZQ8Y=HHw@`&AKq`yzO
z`{dMpZbnI%9ZL;e=J#j`1cjp*g3F6JK}O82X!CbKVR4o-?Zlp5ZCfkD2w^@-j&Lg$
zYvh^`ZD=C&v}JlK$mSsJQ&yy-78B_X3TuR3=I4mK9wx|W9Kf4&_Kz0gm?SObu>Z08
zk=90iygTxrkl?n%z$`z<=Z}{|5}HXH8bq~VBZH1}-L}tZyUJeO_=HP;fd)jy{$^Gz
z!201ScL(91CfT>#N;Flag0}(1@1jPg@nQvNHn#lms-SMy3sZQdT<$4v_1_(XVIN(V
zhssFUOs(P*^o8lzYW^?^pO+r8BQ2xv(--}Y{m0AFRrP8aY6DFGo5+7XFRSkd$i3e?
zqAXnW#P^g?Fc=2Sxs}*xSC>K}{TlYI9C&f-d(_;mzmBE##WCn<>I}-O?51cLd~~8%
z$)2VZOe}0DO76PFgIHY#ez+m}O^W^*zp)mTz3pT>@WRut^<;PB_q#BxLa(13A-m@B
zh0<(9@dY0BwXt-P?yX1VL!{zi@=y}*^3wJvNd{7&hH{H!fd4o^(XkwP=|Qm<N-CJ4
z7-cm^hN!{q$Q4NYazUX^8i(+#qKh;z>x!GU7BRd~Wpp)z;cPajF;UXV;m=On%UROs
zC}e+l9oghmdd}Zs+212su%W@Ijw2<8?;dsDE;%Oz3m2e5;Z$pF-_L^W9xOEu)>RHc
zqTm-vT&b}AG}iitmezbjqAIKwoWvt6)xCA>*IS7jZ@a7$E1{MFWFh}S^4>%es6%jS
z#a{K++|uIZyG3xhBMjfV+UI=mI-|jju$+47&ewqcdGl?|RW&=SiVVs}fr0{tjCOw(
zOjTvH(X(xPr>(KJF0qy^fZ9OqoJs%YCu}m8b<ZtA95jsVmap{Gb|P`ORqpSJA|E6w
z$_$W_#0zP16CmbR?AoZ<s?Xonk@fIU0RLkStxc3#RC6MYdw@NG{g>tMbWHU~XNHUa
zlwc>vt2T+9_|xOpdf)CjR*|$2+0|2TzW|GTtgV)kH8%~G^~0}rxD2fKqT;(I4z<3$
z{sGu3&(PpD%?o}5&AqmLj_)kqA8T>nYG&3W_h^mlhz!#6%glFt!chdaulF16?b;wG
zBlE@8dF~WVOIFTLEazCU))@Nzkd>EbiIZ%IK*w*enVG|4kH)sv9#3I@0Z)4-Aa2w*
zTjwOWaPi9hWu`!df=QK;vG!mLnaEIaYNTdweS&%mmF>ZrSrB6`HD!P<<HXp6&EVEM
z;;m2Mkm;_#eePpzI0Zs!o)jDC(3*;!k@xE6y4`W6W&VQ`eFpEE@(G%a0QTm{+VMBM
zK*&Aqf$|n=Teg;dxAs<r)Etr_uF(Ot;|F^-1B3b3;6ZTtT|nE14tD28e^e`mo_&$o
zksg>sl~Z)q!%Ks>ixj8C&gZflG8$cwmmUQG)B<@0u$_9V>FKuz%tnJ#(<ir#P}ayC
zO0bKiiB<{Z#Fks0u_1&|x9$fZxy(?B*3|u|aH-bL#PIqWpOh4}$$En~Gz6gU&^#|P
zd%Vr)<>9e~(!cPVbZ&8bXmvL_X>v&r%9ZVt6(REBx{ux+%xi;&-<{@b4z*H${rRlK
zW_5}qhs{naeKL<_ra#YAoxu*57#&*7O9!iuVSv$_So+Shw{>Cx2u&Xm2h?8Wr6ya6
zgZ$*>2|`|FB{c4MY#%Q(UcQ-;;uc*RX|1S8?-?p_^WqnP+=H`^p78_AI_sN!It*E1
zu(!&tWxwJT&$<%{!73^;t>)MMoY-8e&~d!O1=rxB+jxSit4-{3g7-Go(6xzO)}+x)
z*@Gcg1ccqtS6O?dnXBZD?>mT~Dc6)alXe7)Ggt8|^d&~n7ON%s97MCvkm-QtdTh{+
z(cnDrKngT?HyszU08Whv*NYOO=%G&4FIQ}Ee^uZNRt~ZdiWu-t1QaVFA>AjkaMV5n
zRN>i?H~g}9>H64mBq@8~6B6Xeg=UO0bXuua4kd&O!;#=2K0@<6cq_WdR2)?UgFZsd
zu$2p5c=nxz0nW>i1E}YTOKm&UTMVVuA17k!pqs8KsG+B8JPp%!?-`sCuJ#~g7@R7#
zh_&AdE(s#VSHxE>lHhWoI=fqM#3Ir)z#T$)CdE|vy=M{{FU1dv1*JQ0$%d@If!f2-
z;8>;<Z;%rJOAmE>sBlbphmX+B&qWf17iEncNs7&qy*1dn@R=X%HD)0V1F~0^A{ES5
zA7OC#GPn@4vDsAR6sAehN*zH!0uqqagM&U=a_%T5Q=Uqpeuq($p%N?XIY@iz%7H|8
z#UeRZK?)I$%T9(q>1dXkuN@{}!1BAAV#{31uS_cjJ421L*+U&xWnk-NA$E#*ssEVr
zhP{@{nEa}pRanABPh!x_@SS+r2DA==$R_OwZOO(74<#0cC>2-QNTT=;k-d{0u!Oaf
zU*!-*-+_D##HgI8i=r(Fu7r+X(|Uxeu?D+`G>Ag_Kfr0!^QxNht}=q$MG3L*Hq2G^
z6O5TiuUTETP*%2CGr`@!HVl8u{$}&XUK_PKq@8ZMN?=>~Yf7;M`3E;~mlnkQOvjNv
zLTOpC0f*gm(f1Dl_uQ8qv~Tc!BPAmpp|x#v(@COBP~a=Zsm`2rM9RxRTkat3J}JW`
zcUHxc))I*Oqeu;XUE^p?chA}FLU|^~7iSlzXZ_i^ZGW8-DR7js7g$@P-lpr%O-)4<
z`NNX9qLO~=Xz6Rp@P4!0n>3jFy_iKdWK3KY8Aj%|EQ~!n?UQ11Akxn{^W5XPxdA&f
zp6kK)aCQ^!?9+*76FdBh>2X!-*GrB*AJ|Oh8`Hht+y0@+7J`l%++Oee0D%^3vkNak
z{9oO~Dbq#fnv24hLx?N5e)6i!lj+zwJ%Dl{j*r%28lO6Tf-&#r+HGUK(zeu~Xe(<T
zC1iuj@VD@quFs`E$}Y<FxU%5S10so{{n5d?aBDZZLH{4*?&jaHnT`qAf{(JL3^%@K
zDI<?Z%1hwhnUTACE_NXuzlD20414LHHzDN8VXg2tz0cN?8F?Ag(cAo+pnBg~M?;nq
zu<fmsA#Pu|)bB|7hlNP_s6VG%K!+j64?bF#^&Gdcb&N)SW3RTc%bR!ILgl3?<2+7f
z=BaBPe-Nv%4i=Y}08NiB#2uX-N6^}CVd+Vu8=)K6bJMd!mEJVg?TpXG-m{S=6Q4v`
z;d$28g#o2+K75#?SQuU(b>139c%M>9%pbJGs6UtiJ<=a!r4Q%4zibzFEw&egD|&gK
z4y~fxHoppBaq3P;CefkzmM8&1WpmdggDH`d;G3!LS!@`>7m7ZNqXh;%Talb>Z&d#s
z(?-=e+JKS4j_ptQVF`tLQxb4QZkAsBvPuHQfAgipr7rYfvUoHT{6{?H)Ow?+DqRoy
zC<5tUDAHRnJdpgF=^Z8Mz;VpRL@K-|Zi$GR`hV?tYwrt9XvORHYe;)S3!AIIEI**M
zEPNOfE*^t9MbA@gBqR|}`qpMH`QeSF6KXuTd3p+yaaFD>ZSfqgEDXI+t0(Y)nwz;2
z&TtsXs97;6vxv;k`?{@@f&x|nEjL6jf%Syi@(QL#hT6S;x*VIaugIz|=A(se<}_ur
zr%(o2Q$-t+no-@~b`aQALv(kjAc-R=O*9%*w%@;T?_!?}oPJ;;^&MdGe~5;{)K6>d
z=_tFrTkg@ckXGNNu9|djX+VF(+CD|8hs2Z-$r+tC?-80)F!|$249f8Ib^bOEIJ!E!
zTMxfodbrfb_Use*D`<Pxfgk{pE79APC+GgY{+PtpUNI!RA^%P{aq{<k&*U%U-t(<W
zgExlV8L8Th#r%HWy>rXU$Uht%r-yQe6JeyLsE(jzx38HLd&yjFo8dBL#;u=s2bBS7
z_^(c2Oj$6}1UxW76@(+&T{*PXOP-obpFiRat(5l);MPD?cse_$xFxRs;iUj~W!dL+
z&Wb!Q9SW8M^p-7lyMPS8H^{dko(?nowJ;?ij#lLL>gRhsr*!aN@yD0`IE}7Um%7M{
z;gLwfnO_tPmyq`du5TGqa!yyT2(NV@1DeTWy^TE*Jh(S^E%f9hY4?E((UBd^<UVze
zfkNNT15{n^-n~z+j9CjgrmaHW?nG%d;SL4=8jh3?BtSTUXy`MAHrH|x24ISL5Doj{
zI#LoQgY+h<FgB|-G*DSu+m$eJgU|N8MCWSKMMi2kmX)5Na7(Cfoi-x27<B)Ix#DJJ
z4bnkJHstXZs7p-rsepy_e&lytR-YHhjmk;&ZT!jHAML=VS7XnDw6G~<KsHKczfn8_
zN;4YX=s_BE>S=o*KFP;E5I1bgkBS=9)MTcwZlwzGyc?Aab0w3rdif=F=>gXR+uC}9
z3N8Xa;_;-8Sl4E{4tP9VA;*RgUcIOyT0a#h^Jxhh&%oH50;;wuy|}m`{Ztezp*nUx
z3@t}>cH=^Tgu~kEHhs~Vumdq^MJ4|Ay~%TF(|}`sV!uGNE1DtperHwnc3r^xu5KgT
zzCCpXQ?)_~#8WCfJThG;CQwO)D{Xs`EsDRsn=LxD#pz-G4ThL-QmfG^$$a7%M=|aZ
zdQsyew7cPd*wZ%U&{)rcx(xJ}M@izw^1!s#8OW&`Y~{j3I~E&Gnzr!mELGAQVrP@~
z105*N&(0)fH=8;4TVF5gy`11&&=;{CZA9acFLrY67-A)z{+%NhckhRPJeFj1y~b+m
z9;ip?kTkS<$8cu5cW4n{fgQBHdt%YW?);N=t!`_iAeX;8R+ie|ua8i~FfPJGC<+gS
zxstt$lasD^Du=;ANx?fNb>xxkHNS{;+mT6QM7_aB1gN6KU*uY*jE;Dkf4jEu1tK;m
z3}sV1sl8cUjAl3vmUQ2DhqkLqiTeAa@c7~%Z@wtT7q~w7OFvZmcXiEL;`3{F9zv?#
zd`??n>~$ZvJ63F09I|(J*Z7av$47*TKAy{WyIg)GQD@ggxV)A^muxcS)Nx>|ASjkm
zoi-sGA?r&sL*K3wdsWtm;&}nVSkuTGB{8b|9nASnu7|J?bOj$JF$dJ7Zqpc}uSxh(
zY%7}Djx5U2AOA9Z-&f8*?X{0ANYOJMk$O+VF<k!FA#QOl0$U~eXEAG0@jbc5IZg`b
zq-UmcjV@{WH$kmq8Xo`2-&i4|C^6T%MxpNW5i#Rh7rX`hhSRQDiHEVJ<l$11THhuu
z6`!}SqHT1K*EZZ29UKO4FlLu44Q{Vidle2>7L{y*ct^E`{;-w>YeOZM>nhrG5bm#u
z#^(~VTYD2&M{zZPaSP_@J@SWP;Hy7Zr>)@a%UfUFW+Jy?D<FzaFaw%ItfRt{R!^0$
zn>r+P;Aet}*yD@qVT+e4XKwh3i-!|J0${{th`5pwVb>vx0ABlZe8qMjplhPtiej({
z@l~t&mypr;s?j~HvIRFf*H?1;#2=~*`Fj?6Da`JVJ{b_=E7Ej#Z{YPc*|eAvC}<Ey
z?RKcdJ{G=XQ4U4YpKm#<e637~$nFM}DTJm~EL6~aBVQ-xHrIa6%_V5L6yW3D_NryB
zV;@P?lh^hYrdFKy3G}8%k7tpzNfJ+4UTwav0Si>7ZKcm&-LL9g<lblK1^Sam?MAI3
zsT9*m4Kw3<E>^i+T;^#AILnrv2{JA13DE4e-c?5@lq2}%F0_VZ;5oE6yQ1`QuH1og
zf|p9+&*7@Gy>J=wvX<#RxSXL>5&Squ6j}OW@wHiU2e|25ryc79BDaoxM-6We=5k-7
zC=+0;>y};jXvKu5AtGa^v@czK3XoxB@|j7OcN!-WT$ZZf)o!{A7b3E?RojV3`DN&_
z^KV(LCMSduJ3*a_xZASWXeX@QN$G(Oj<Y$+XG6LvV2^TQj=r0IG85AuRSELBLBaIM
zEbU%7gqlbyZ#Aj%B~vXeY&47&u1bPq`1}M09*`(6L8dk~_=l!3GJGw^JtPHX8M?9t
z8j^9Kog5x_?vKFOK>n2sUF~Wxi!nNiBg|g%{oCOsu{Li$<$F*;d$eYyl8?W(opnAo
zEW{UTP#cLk%h_dSXiH%hut9$5J%FK;>X|pIXrB?Z&W2T{0`!hsW8_988U{S!(;D5{
z>&#VwyfNKVw!%W4H>p~!qn9M$2J)*cqUcsGP%IvfJNsou&sLWbv9cQ_!oG6}*~2DD
zT?u1xaYe+h1hjr?u&^(f%Q{@T(!3c=DBrQ&<2TrPNt0=1@LMOzwYD@_N5e)wJ(O&?
zESH%)Kd&yc=u+_8yFj=fEnmwU!ip?uyVsv>4CZ|WHgd}|x{H!_d#fcPoR*A@scv+K
za8mhu<!gll`(9ADubX<`sYF~NKNiUR$Y%WYHYPb4Nq4cX!nphTiu-#Cg{P<}L<u#V
z=(RI>__;kD^UIt1-mdY(w}(Y<y!>pa;u^NtsUql?0J4ZJ9z8d^7Y%Mi1d}6?@)a)T
zga#uKuClI4bb<qrZ*r47U=m^Xh`;=OH_!eyftVNK2n3%qm%pLZM2<Afn=##={*p_3
zE8^#_DIxWSWh7NR{f|_rI2TpU!W6+EX+m!`_!-t4zPyC`<-n{R3aJHO`J#B{^XG7b
z6OH}dbrbI+;l`#1e}2ya{!vj~{y%fYYbJIR-b>wEJX!;z7FQIkra(5Xo^A%E=1&7X
zN++%@qhqe+>{W-FOr+!M$JBfUw@f7QC8G#P5MUy0!jBj86xuYiRtW@dyPAJv;)xWT
zxy5JNsoC*&G5;o_`t>H<a!*Icd@)^`Vhs_`nV4G1$!`*mr6FldP6+-%dXw%+8MD{)
z=Z`aahS^W<0tW$_;fAU#EyJNN-=95Y=;Mn?TCq$HKhj8W2ry=A|NgBRJ*%#eCVJUU
z))Tizvoe)BXS39Uo0&q4)a6R96|}3BqG#KcDV6oe?*Ma2@%ZvCb_>2ELECPruwi$_
zilD^9UN3GP^$;^=iAFiWc&_t#g$qRPMSiS^Cg%2Ptv)R~otsCGYn{DbA_jepj;aM}
z4<ma!wr5x0a7hW9%JGD?&gicfF75XUSM=0=It+Q~_w3p@xA~M85G&9yk?3`{7)7C?
z>&qQ%rN@8Ha5|%x6m5>J>;!`08?+R5bp5ew&R##e+wbn?-UkFmr&cerbeRoemM!zS
zs9F{6_$ebKj2mB#kgzR1qfys#{8a@j{5>~=9q8iBLap>E@3Kckj!0j;*X#*(>8jMZ
z(on|27<rfrx#>#SGC{TaxKZr56-BS}HJM?9kPoQ^U1zfs6Fbom=_PsJw}kVPwY9b1
zv!Bsf+-owcjAwiK{&*CcvA`-2=$5RnIeHmrM#!Cg*Q)CD5N~3A&3)WI{|c9df*?Nj
z+sz-<Kir~56(~&<svt(EY(%0*&Uki%FLeFk`wZ~;eQNk*uG5{Sa2!yu|Cm~`TV5zB
z-d#4*OXu<k*(>)PwGW$BT+Y%CO)RcrSz?eCHY~!`qLy7Wx45xYHfVYAn{uIkeBQ!a
z%V4B9_f$PKe`|ay+f<j=YVqS&LJJmEndbNx>p;(eW<a)HOQG44owNOWAP7sL8Lo=n
z;p5nvZQq9k@yH5L-Ia)o$m<LC7KZebg<K*xaJ${Dy-^M}5rQcBiBTB|CNA_w$`dno
zJt_%bUYKeI?suu845Z*J;}|k_8KX@5xB$u<@}^Lm%y)!bH|(l%MyEXRajL4!(ezXj
zB{{`o_IAWv6Q7H%2z(7)lQM2ie*9FCpyI9}S={QPgsX2ye9v^f@GPbH*B(!S;Y3C%
zd#e);jVu8IzP_)1KPEBF7co#A1%_w`G~+WPLWvA;e#B~x`upSeZbi!3hG~p3!Ku#z
zK=_I#00{(8()2cV8^=P_jYhVu)zE@z5SxlZr08j#PG>q;Tce^Ft>U2A2UqftdS#R(
zjIxs^pE53Cc-i5~=jlr6y=P)h`y5T3gOjGI?UPxGHY<R$L71LIO~%sFy)P-J#S~Bs
zzZO`2qS@<4U8@=cEfeKs>x|7eYHdS7Qf1c_XjMT!Y5e+DAA;vxk{#)KFJ61`{Zl)@
z;Hffj38hr6C}kRz;uExpip1-qQ#G6ggZ)V{%1BL!@eNM@;84$e0}3V-ASijgrfOBu
zLe=cs8f2P_WL4T5d)4Zt22G)QSIlF5tmKK*eJ3sE(mQ}lfEd*hi|mJeC7kJj6P&cA
zkD>O*Q=-PUc4`JIfF)$i&CyiPMG^Y4yU}Zza;{W4mY%5HL4VjRd@JYGLAB_&!9$y4
za*W)j-s{Ec@tYfy@YJNc@QxZMHCcZI*-cYnG<iIWQ0PMn+m(Czvi6&o7uOSn(}L>g
zFeGcb&Vl+4IS2&WEP{YGWlomKSeAvY6Bm9&IPyr2ueh=&nR4$I7T0QCQXfMUjl#1W
zwc2RVorqC3IXsy|(=&<eW2|%K!$hD_(HA23J@z5cdZ^6Qiy8j@t?EP^0D!&p)C<7(
z$K81|2!t-$a$IXY9y-5YUy&S8DZcV+``bn9-F=ft@Rm^s$P@P`lB%K9<V*XNZ|0QC
zuX>~V*;ov@$|zDeQ(LfyLE?RgLKUb-qE{5Pj|LHJ3_zBN?|`k7kvpXMl6E(Xh<IVQ
zn+_kh#@`nOG8LIB-dF^+Rw+8Z=1%U+DpNz0MAi3*MsB`?_}dls3d^<!Am+aFWO8~Z
zlZ#8y&ujI#OU*x%pH(k3Zw4*+-E40k{;+n&)ycv*bL&od+{Gg_*%T#P+cC%-&Cq%k
zm3_vfIug&Np3B&lyuPcp<%*y@{B0A+vX$Y_=^ZcN%=T#NBp{I4y^R7SE(o+`@d3c+
zYA$4q;ERqxRza+AKd2z00uitE(?nq~N75$Eh>=MvdlcHOn`ztRnO}C$hJBLi>Q9@h
z>cpqnR+jeGzx^YEd(QBErtyfT!E`34QGv>4k?8j7_6BWR>E+L#6_#Gy+;YJi(Hx`a
zv+j+lr-N7{*+z*q<;f)P4!^cf`X-gRiQQY*2L3wRDd-6glv`rJ&Gby>zbiZZ{%H$g
zfw+q4!RU&!`!IF((;gY^bp+tj4gFrXqTk>1o3u4t#zkckUfl1d%jO)jZa{udx%D9S
zIkn*3=l2LQBLcy+vAQ^Vro1M9fA)B;hhPU_#5>8cgwrcR<sca*-E6Wb`tqJ`y%@Ph
zX!A!zKBkX2Km>`vLa}+v0YCdfRsEvCEsVzif|fCLZ_+nODE6KrtCO8F!De|qntkJ&
z*Xs2JCueE7wT?Wd;zG-K1^OTmhAb%f?Pp)sg*vJ3sQLA2&%XVFa*%?Y9ti9#P~*3J
zH5IsFhdWq;{D8adE>ZXA@Ty&qu?S2QL`Ae<N+M+UzDu>CZ8WIUvF}~7Nie1+wOZM<
zIKpsG>^v+)H@oR@Q;N5`^dX2-(uXTTIaO~yks$@ev3%qwylV-f$0n`<`eR;+BG^Wr
zW3qNhhkmqYD`5juNup?hYu$9{h>+DHzSTj&ts`g|;l6k{jq&;R&ZQsCEJ}D;Zp09@
z@?JL`1W30ds?I(^gRdAQ{^fHcwHB+jP*zIkmMow3^o0xG7hOR6Ikwr+=|Xq!AJ`4K
z%P@0Wo@H2s1R=N+Q-1n|jprjr{&_s}=m=JRSyiXS82O@F8udYDnLck^(ulFhL>t&m
zm{ZFSCiQ)`qsy@IXYARQb`7K$*Qp7v&u9@Z(jgmiftqC%GC>*@&V0^SYrNy%dZ@1H
zY;p%v)9NJIG$C$BZ?y?iEA{7bg}wGyBRl?PC&d4V>$CJV`shtXo{P(#&*c_2LS-=F
zv4jFfsQ$h<Eu6qyb@u9)pjh?IceolcRe_&Y-ZvTc{E3Rm7z_v$JuWqyP6W2QnSbLT
zhg~B*K1TDz2V?crT=2LN+~qr^Bl2?u;=d1RAe-GMfvPi++I8iJ>Op6tf^^-Irprml
zR*R#{ipH1wTz)P4UuHU-GX3eX@a4ySIlHs~>qMOj<L_ln+}l)X`S`f7JU85y=fv)|
z3zo<uhMm(U3hZfBw3oLBh&VkYpSnF9$qZ`e{|f4w8qIB*x`tEr`9AKmZi!E6{Ww~Q
zi_}fQ(1h;sX;@9#tA5IB2@z#lbzQ=|a|C+b|9Z_?0aeYN^`17OVS1f?J6-%OYz*}Q
zd1mH*BU_O`7w|;u$Fc-U_=k*Z`~K`j`5V#eBc?K<6M(Q{u{XO5wt-)g3H6#zbe(l9
zuT?BGB&mM@rnIfDI|n`Q+hc^3^C!esCX{V>J0=*;Qpj+u8`P|l_+L&6cd{Z@u52^&
zoTnZ~<B?oL5WcezA}DfH);!_6@P%Zg+{!&eFuWvVrZ}|CZ7U6Fp~)Ivt0#UBpAh7B
z6PpI_AUQ`y<OQYm=AG6+1DLMo(0K-|nL@n*kK(bnx1)&cwU~vLzm-Ryt`Jc}9bJiy
z)T88jVxih!O)c~W(cWIM_-`o@32{oO^!-BgBy6l*Z><Gx&39A#Bm{e7M@=|_v*qhg
zzX+xf{FQnHByRL@e+`pkmBbmVbp1R{HT62nL1ZvWPn+F9EG~o$Zz9RV-OXf<;F!az
zo|gx#j2k&lxmX!Ky_I)<-FRc<bAu`tfT1Cn_l^b}kvY?NklzaWZbv`+7ao@qUO3q<
zbs*{F^gQ<B%8pb5>khrh7`7)2SDPGndzHVWiO|Xq@XM5ZNS+nZu>#zIc;wK(x-Svh
zo#@y*WXK^hU~~?oL3E5srpPRvav&JUbDLBW2hG2}VpInRGDO#+tmUzL0NsQsWE4S>
zJPO9lZ<aoU{aEOm<@Do;EWs8Z`t_Ypi%^aoJc%Aa@Rw}tW~<RS4x(gLrZW#Nnh-ve
zoymiF{>Vj9mg#H3aA((6yd`q9w<{P{gVZ_;yh<8uFy7#dd{NoQ;cRV$S^Sq(^DriV
zslDfX`D5vOrgBM*`CmjcEkwha4?Wv>k2{rQ+Y-oRw$%8FM^F^Qz=M}@t9Eb>Xu+hB
z;YO{2BxB$j{TI&uzb#Oedwr){#;e)3*wm$K>Rz3&X8bFOD)Xqw(k~=?b*f(sY+3If
z_?DmCJc8ws1Q<qQN|LLn+GE8-0;YUEm%g4A$Ug5GJA51XhYYHXK*T_-(ci5I6x+;<
zu`urGdONPL9_DT&^W(P|F-^DTQD;3X=4@|?r9p2=f^S^{rb0u4a1Z+Tv2<?H!TT>x
z6tIN$gT*&r4<B9zQ2(+m=%|13b*?>esYqVH7IYf@)=!v)&TYMy*SW9uXnKf@=?Fb5
zvXV=9y@oIooWIym(K^)rW~6VZxuo;AmSf-0m$}H|gL4Gw6!1_6N{1-DV!W3TXM8{G
z-(G%U@vP;68x-3+G6os${PVIIsS$(EvyIfEe81OnZY649&MPka&b8#SuK>DoZQ(;$
zNTm`d>Ff=NLtcrA$UB(y5L1sr5Q>C-WWRJRtS3g$2k+eTu=!xleAc8Zj|hvN-dPrS
z7#c|DsUfZeZeFj~Q1c<dU%-<QBv8%bxx8uSLv$Z3UK%bA-i@Bs;Xx8rMD%aP^RiGn
zCVK8L7;PV3E(IhJsyAiVxETiN%bGkx)7%USd9eVFT4(<yEMIu`Jp&K3Vw5xy4bBPg
zk}~iQh)h~0`M3IQqi<WTP+VzhutoT$XV$B2!~UmjwZDp%2_vTp_4{*8;iHrCx0oyE
zMg1#evg}}-;`nVmHA9h~*_z~J<C)O7^*t5MiS+*zv3VoQe8IbU;OSwoJ!U<L(1?5r
zTlJk7*yl-evj`P-<rc0NSS25|8DGivQm4E)6R0FO|H^)fMrQHM1pSVwO1Q19JMsTE
zU1?YvWwR<2JG@;CEvV?w^aLkma#i?45(!l)VDUw2+<poKc5ZT{<ZOw)(zkQ#p6W}T
zt*7FFYm=%h+5Wnw&yO(*e-9#`oHIC0xc_H`)zR$X<^syUa0-kgb3rOoIQo#^m}Ov!
zZyS4stvBHxr<to|u>C_4&vtR^^m*PH)>)i_?vZ@>+uHKq{@bO8=q`Nq!^(mso=~?~
zFt-s@zzNmd4Lg+lgu&5|#i$mjs;wYoce)hv;qxqS1ysm7?er*^{O9J?jkzm2*1tt|
z7S4KSrR1ES-T9P0*vd=6ntW%AVNK4^AC_frC{&U_=5vT@{$JA!?Pphf*4FSm=vz}-
zgka*A|I@KB`Oc+4#`fHexHRO0WKk0CEVEU-8jb@JRyoN$e)EKFtw3}{^t7GWsO)6y
zKy?e~@B6hqmC1>Te`T<@Pi!#5M53$>gz-ea&_&`4G0!1Y6DE*xAXCHN7T_1RU5cAt
z7~2P2<axUL%NB!wK55E-`&>JJ%i9zFvkycg<g<V75d7Ox^8Z?5|G$C%_Q?LPO|zXS
cXOBq9wFA@fUkwqR!vMf*d3Cu88Pm}J10TTEzyJUM

literal 0
HcmV?d00001

diff --git a/setup.py b/setup.py
index dad4219c..32f5772a 100644
--- a/setup.py
+++ b/setup.py
@@ -9,12 +9,9 @@
 with open(version_file) as fh:
     version = fh.read().strip()
 
-with io.open('README.rst', encoding="utf-8") as readme_file:
+with io.open('README.md', encoding="utf-8") as readme_file:
     readme = readme_file.read()
 
-with io.open('HISTORY.rst') as history_file:
-    history = history_file.read()
-
 install_requires = [
     'Click>=6.0',
     'python-crfsuite>=0.9.6',
@@ -41,7 +38,7 @@
     name='underthesea',
     version=version,
     description="Vietnamese NLP Toolkit",
-    long_description=readme + '\n\n' + history,
+    long_description=readme,
     author="Vu Anh",
     author_email='anhv.ict91@gmail.com',
     url='https://github.com/undertheseanlp/underthesea',
diff --git a/underthesea/VERSION b/underthesea/VERSION
index f0bb29e7..306bc600 100644
--- a/underthesea/VERSION
+++ b/underthesea/VERSION
@@ -1 +1 @@
-1.3.0
+1.3.1-alpha