howl-anderson / hanzi_char_featurizer

汉字字符特征提取器 (featurizer)，提取汉字的特征（发音特征、字形特征）用做深度学习的特征 ｜ A Chinese character feature extractor, which extracts the features of Chinese characters (pronunciation features, glyph features) as features for deep learning

Hi there 👋

I am Xiaoquan Kong, a passionate and creative developer dedicated to Deep Neural network Systems and Chatbots.

Some facts about me:

• Ex machine learning engineer lead a team at ELE.ME (a subsidiary of Alibaba Group), directly leaded by and report to VP
• Head of conversational AI team. Leading a team of more than 40 people engaged in the research and development of AI assistant systems.
• Google Developer Expert (GDE) in Machine Learning (My page on Google Developer)
• A mentor of TensorFlow team in Google Summer of Code 2022
• Graduated from Chief AI Architect Training Plan by Baidu Huangpu Academy
• TensorFlow Core contributer and TensorFlow Addons Codeowner.
• SuperHero for Rasa (a popular open-sourced deep learning framework for chatbot). Rasa official interviews and reports about me
• Top 4% contributer for Rasa, most Chinese language related functions in Rasa are contributed or tested by me
• [Book] The main auther of Conversational AI with Rasa. Alan Nichol, co-founder and CTO of Rasa, wrote the foreword for us!
• [Book] The main auther of Rasa in Action (in Chinese:《Rasa实战：构建开源对话机器人》). Alan Nichol, co-founder and CTO of Rasa, wrote the foreword for us!
• [Book] The main translator of the Chinese version (《机器学习流水线实战》) of Building Machine Learning Pipelines by O'reilly

As an active community leader, organizer and speaker, I ...

• I am the lead organizer for Shanghai TensorFlow User Group (TFUG), organize or co-organize events that directly influence more than 6000 people every year
• I frequently share my knowledge & thought as a speaker at community events, such as Google TensorFlow Dev Summit Extended, Google DevFest and TensorFlow salons, influence more than 4000 people directly
• Sometimes I am entrusted by Google as a TensorFlow ambassador to go to universities to promote TensorFlow
• I found and manage the Rasa Chinese community, the biggest and well-managed community for Chinese Rasa user

hanzi_char_featurizer's Issues

ImportError: No module named 'four_corner_method'

hanzi_char_featurizer/featurizers/four_corner.py的错误
包里并没有four_corner_method'这个文件啊

ModuleNotFoundError: No module named 'hanzi_char_featurizer.featurizers'

把requirements写清楚吧，安装后用不了，估计环境的问题

tf2的问题

如果想在tf2.0以上的版本使用，好像暂时是无法使用的吧

ids问题

这两天正在看iqiyi的FASPell文本纠错，偶然看到这个项目，帮助很大，论文里的ids问题让我很困惑，不知道大佬解决了吗？想白嫖了，哈哈哈

ImportError: No module named 'four_corner_method'

ImportError: No module named 'four_corner_method'

安装项目报错

git下载https://github.com/howl-anderson/hanzi_char_featurizer.
cd 到目录下
python steup.py install
然后在控制台 导入包的时候 报错

import hanzi_char_featurizer Traceback (most recent call last): File "F:\ANACONDA\lib\site-packages\IPython\core\interactiveshell.py", line 2862, in run_code exec(code_obj, self.user_global_ns, self.user_ns) File "<ipython-input-6-717af367fe07>", line 1, in <module> import hanzi_char_featurizer File "F:\python\PyCharm Community Edition 2017.2.4\helpers\pydev\_pydev_bundle\pydev_import_hook.py", line 21, in do_import module = self._system_import(name, *args, **kwargs) File "F:\ANACONDA\lib\site-packages\hanzi_char_featurizer-0.1-py3.6.egg\hanzi_char_featurizer\__init__.py", line 5, in <module> from hanzi_char_featurizer.featurizers.four_corner import FourCorner File "F:\python\PyCharm Community Edition 2017.2.4\helpers\pydev\_pydev_bundle\pydev_import_hook.py", line 21, in do_import module = self._system_import(name, *args, **kwargs) ModuleNotFoundError: No module named 'hanzi_char_featurizer.featurizers'
看起来是项目的结构有点不正常
win 10+ python3.6.7
请问我还需要提供什么呢