publish new release and copyrights
This commit is contained in:
Hai Liang Wang
parent
359fe63211
commit
9de17fa1a2
61
CHANGELOG.md
61
CHANGELOG.md
@ -1,54 +1,69 @@
|
||||
# 3.11
|
||||
|
||||
- 支持定义查询词汇数量，默认 10 个词
|
||||
|
||||
# 3.10
|
||||
* 计算编辑距离时去停用词
|
||||
|
||||
- 计算编辑距离时去停用词
|
||||
|
||||
# 3.9
|
||||
* fix bug
|
||||
|
||||
- fix bug
|
||||
|
||||
# 3.8
|
||||
* 获得一个分词后句子的向量，向量以BoW方式组成
|
||||
|
||||
- 获得一个分词后句子的向量，向量以 BoW 方式组成
|
||||
|
||||
```
|
||||
sentence: 句子是分词后通过空格联合起来
|
||||
ignore: 是否忽略OOV，False时，随机生成一个向量
|
||||
```
|
||||
|
||||
|
||||
# 3.7
|
||||
* change import path of utils in word2vec.py to local path
|
||||
* expose vector fn
|
||||
|
||||
- change import path of utils in word2vec.py to local path
|
||||
- expose vector fn
|
||||
|
||||
# 3.6
|
||||
* Fix Bug: compare 保证交换两个句子后分数一致 [#60](https://github.com/huyingxi/Synonyms/issues/60)
|
||||
|
||||
- Fix Bug: compare 保证交换两个句子后分数一致 [#60](https://github.com/huyingxi/Synonyms/issues/60)
|
||||
|
||||
# 3.5
|
||||
* 根据实际情况，降低向量距离对近似度分数的影响
|
||||
|
||||
- 根据实际情况，降低向量距离对近似度分数的影响
|
||||
|
||||
# 3.3
|
||||
* 增加分词接口
|
||||
* 优化分词器初始化加载字典
|
||||
* 使用jieba分词源码
|
||||
* 使用 glog 作为日志输出模块
|
||||
|
||||
- 增加分词接口
|
||||
- 优化分词器初始化加载字典
|
||||
- 使用 jieba 分词源码
|
||||
- 使用 glog 作为日志输出模块
|
||||
|
||||
# 3.2
|
||||
* 将发布证书改为MIT
|
||||
|
||||
- 将发布证书改为 MIT
|
||||
|
||||
# 3.1
|
||||
* 对空间临近词的邻居进行缓存，提高返回速度
|
||||
* nearby中处理OOV，返回 ([], [])
|
||||
|
||||
- 对空间临近词的邻居进行缓存，提高返回速度
|
||||
- nearby 中处理 OOV，返回 ([], [])
|
||||
|
||||
# 3.0 - 更简单的定制和配置，增加了额外的开销
|
||||
* 去掉nearby words, 使用 kdtree检索空间词汇的最近临
|
||||
* 增加了对sk-learn的依赖，但是减少了对词向量的预处理
|
||||
* 优化了分词所使用的字典，也可以使用环境变量声明主字典
|
||||
* 支持自定义word2vec模型，使用环境变量声明
|
||||
|
||||
- 去掉 nearby words, 使用 kdtree 检索空间词汇的最近临
|
||||
- 增加了对 sk-learn 的依赖，但是减少了对词向量的预处理
|
||||
- 优化了分词所使用的字典，也可以使用环境变量声明主字典
|
||||
- 支持自定义 word2vec 模型，使用环境变量声明
|
||||
|
||||
# 2.5
|
||||
* 使用空间距离近的词汇优化编辑距离计算
|
||||
|
||||
- 使用空间距离近的词汇优化编辑距离计算
|
||||
|
||||
# 2.3
|
||||
* 计算相似度时增加平滑策略
|
||||
|
||||
- 计算相似度时增加平滑策略
|
||||
|
||||
# v1.6
|
||||
* use ```jieba``` instead of ```thulac``` as tokeninzer.
|
||||
* refine console log for Jupyter notebook.
|
||||
|
||||
- use `jieba` instead of `thulac` as tokeninzer.
|
||||
- refine console log for Jupyter notebook.
|
||||
|
||||
2
demo.py
2
demo.py
@ -17,7 +17,7 @@
|
||||
from __future__ import print_function
|
||||
from __future__ import division
|
||||
|
||||
__copyright__ = "Copyright (c) 2017 . All Rights Reserved"
|
||||
__copyright__ = "Copyright (c) (2017-2020) Chatopera Inc. All Rights Reserved"
|
||||
__author__ = "Hai Liang Wang"
|
||||
__date__ = "2017-09-28:22:23:34"
|
||||
|
||||
|
||||
@ -5,10 +5,12 @@
|
||||
|
||||
# constants
|
||||
baseDir=$(cd `dirname "$0"`;pwd)
|
||||
export PYTHONUNBUFFERED=1
|
||||
export PATH=/opt/miniconda3/envs/venv-py3/bin:$PATH
|
||||
|
||||
# functions
|
||||
|
||||
# main
|
||||
[ -z "${BASH_SOURCE[0]}" -o "${BASH_SOURCE[0]}" = "$0" ] || return
|
||||
cd $baseDir/..
|
||||
source ~/venv-py3/bin/activate
|
||||
python setup.py sdist upload -r pypi
|
||||
|
||||
8
setup.py
8
setup.py
@ -13,12 +13,12 @@ Welcome
|
||||
|
||||
setup(
|
||||
name='synonyms',
|
||||
version='3.10.2',
|
||||
description='Chinese Synonyms for Natural Language Processing and Understanding',
|
||||
version='3.11.0',
|
||||
description=' 中文近义词：聊天机器人，智能问答工具包；Chinese Synonyms for Natural Language Processing and Understanding',
|
||||
long_description=LONGDOC,
|
||||
author='Hai Liang Wang, Hu Ying Xi',
|
||||
author_email='hailiang.hl.wang@gmail.com',
|
||||
url='https://github.com/huyingxi/Synonyms',
|
||||
url='https://github.com/chatopera/Synonyms',
|
||||
license="MIT",
|
||||
classifiers=[
|
||||
'Intended Audience :: Developers',
|
||||
@ -35,7 +35,7 @@ setup(
|
||||
'Topic :: Text Processing',
|
||||
'Topic :: Text Processing :: Indexing',
|
||||
'Topic :: Text Processing :: Linguistic'],
|
||||
keywords='corpus,machine-learning,NLU,NLP,Synonyms,Similarity',
|
||||
keywords='corpus,machine-learning,NLU,NLP,Synonyms,Similarity,chatbot',
|
||||
packages=find_packages(),
|
||||
install_requires=[
|
||||
'six>=1.11.0',
|
||||
|
||||
@ -17,10 +17,10 @@ Chinese Synonyms for Natural Language Processing and Understanding.
|
||||
from __future__ import print_function
|
||||
from __future__ import division
|
||||
|
||||
__copyright__ = "Copyright (c) 2017 . All Rights Reserved"
|
||||
__copyright__ = "Copyright (c) (2017-2020) Chatopera Inc. All Rights Reserved"
|
||||
__author__ = "Hu Ying Xi<>, Hai Liang Wang<hailiang.hl.wang@gmail.com>"
|
||||
__date__ = "2017-09-27"
|
||||
__version__ = "3.3.10"
|
||||
__version__ = "3.11.0"
|
||||
|
||||
import os
|
||||
import sys
|
||||
|
||||
@ -12,7 +12,7 @@
|
||||
from __future__ import print_function
|
||||
from __future__ import division
|
||||
|
||||
__copyright__ = "Copyright (c) 2017 . All Rights Reserved"
|
||||
__copyright__ = "Copyright (c) (2017-2020) Chatopera Inc. All Rights Reserved"
|
||||
__author__ = "Hai Liang Wang"
|
||||
__date__ = "2017-10-16:14:13:24"
|
||||
|
||||
|
||||
@ -12,7 +12,7 @@
|
||||
from __future__ import print_function
|
||||
from __future__ import division
|
||||
|
||||
__copyright__ = "Copyright (c) 2017 . All Rights Reserved"
|
||||
__copyright__ = "Copyright (c) (2017-2020) Chatopera Inc. All Rights Reserved"
|
||||
__author__ = "Hai Liang Wang"
|
||||
__date__ = "2017-10-16:14:13:24"
|
||||
|
||||
|
||||
Loading…
Reference in New Issue
Block a user