结巴分词使用
Toolkits 综合NLP工具包
-
by 清华 (C++/Java/Python)
-
by 中科院 (Java)
-
by 哈工大 (C++)
-
by 复旦 (Java)
-
by Boson (商业API服务)
-
(Java)
-
(Python) Python library for processing Chinese text
-
(Python) 纯python编写的中文自然语言处理包,取名于“牙牙学语”
-
(Python) Deep Learning NLP Pipeline implemented on Tensorflow with pretrained Chinese models.
-
(C++ & Python) Chinese Natural Language Processing tools and examples
-
(Python) Annotator for Chinese Text Corpus 中文文本标注工具
Popular NLP Toolkits for English/Multi-Language 常用的英文或支持多语言的NLP工具包
-
by Stanford (Java)
-
(Python)
-
(Python)
-
(Java)
-
(Python) Gensim is a Python library for topic modelling, document indexing and similarity retrieval with large corpora.
Chinese Word Segment 中文分词
-
(Python) 做最好的 Python 中文分词组件
-
(Python) BiLSTM+CRF与IDCNN+CRF
-
(Python) Iterated Dilated Convolutions for Chinese Word Segmentation
-
(Python) Genius是一个开源的python中文分词组件,采用 CRF(Conditional Random Field)条件随机场算法。
-
(Python)
Information Extraction 信息提取
-
(C++) library and tools for information extraction
-
(Haskell) Language, engine, and tooling for expressing, testing, and evaluating composable language rules on input strings.
-
(Python) IEPY is an open source tool for Information Extraction focused on Relation Extraction.
-
Snorkel: A training data creation and management system focused on information extraction
-
Neural Relation Extraction implemented with LSTM in TensorFlow
-
Information-Extraction-Chinese
Chinese Named Entity Recognition with IDCNN/biLSTM+CRF, and Relation Extraction with biGRU+2ATT 中文实体识别与关系提取
QA & Chatbot 问答和聊天机器人
-
(Python) turn natural language into structured data
-
(Python) machine learning based dialogue engine for conversational software
-
(Python) ChatterBot is a machine learning, conversational dialog engine for creating chat bots.
-
(Python) 基於向量匹配的情境式聊天機器人
-
(PHP) 一款开放源码的PHP问答系统,基于Laravel框架开发,容易扩展,具有强大的负载能力和稳定性。
-
(Java) 一个Java实现的人机问答系统,能够自动分析问题并给出候选答案。
-
使用TensorFlow实现的Sequence to Sequence的聊天机器人模型
(Python)
-
(Python)
-
(Python)
Corpus 中文语料
-
密码neqs 出处应该是梁斌penny大神
-
(for training spaCy POS)
-
使用2017年6月20日中文维基百科语料训练的脚本和模型文件。
-
基于维基百科中文和word2vec训练的近义词库,封装为python包文件。
-
Chinese_conversation_sentiment
A Chinese sentiment dataset may be useful for sentiment analysis.
-
Chinese Emergency Corpus
-
chinese conversation corpus
-
Datasets for Training Chatbot System
-
通过python脚本从巨潮网络的服务器获取中国股市(sz,sh)的公告(上市公司和监管机构)
-
TuShare是一个免费、开源的python财经数据接口包。
-
[52nlp介绍Blog] OpenData in insurance area for Machine Learning Tasks
-
唐宋两朝近一万四千古诗人, 接近5.5万首唐诗加26万宋诗. 两宋时期1564位词人,21050首词。
-
包含了中文命名实体识别、中文关系识别、中文阅读理解等一些小量数据
-
中文姓名,姓氏,名字,称呼,日本人名,翻译人名,英文人名。
-
中文分词词典和中文停用词
Organizations 相关中文NLP组织和会议
-
Main conferences, journals, workshops and shared tasks in NLP community.
Learning Materials 学习资料
-
Stanford CS224n Natural Language Processing with Deep Learning 2017
-
Speech and Language Processing
by Dan Jurafsky and James H. Martin
-
文本处理实践课资料,包含文本特征提取(TF-IDF),文本分类,文本聚类,word2vec训练词向量及同义词词林中文词语相似度计算、文档自动摘要,信息抽取,情感分析与观点挖掘等实验。
网友评论