hankcs

HanLP. Natural Language Processing for the next decade. Tokenization, Part-of-Speech Tagging, Named Entity Recognition, Syntactic & Semantic Dependency Parsing, Document Classification

pyhanlp. 中文分词

AhoCorasickDoubleArrayTrie. An extremely fast implementation of Aho Corasick algorithm based on Double Array Trie.

CS224n. CS224n: Natural Language Processing with Deep Learning Assignments Winter, 2017

Viterbi. An implementation of HMM-Viterbi Algorithm 通用的维特比算法实现

multi-criteria-cws. Simple Solution for Multi-Criteria Chinese Word Segmentation

hanlp-lucene-plugin. HanLP中文分词Lucene插件，支持包括Solr在内的基于Lucene的系统

TextRank. TextRank算法提取关键词的Java实现

LDA4j. A Java implemention of LDA(Latent Dirichlet Allocation)

aho-corasick. Aho-Corasick的Java实现，针对Ascii优化，支持Unicode。

TreebankPreprocessing. Python scripts preprocessing Penn Treebank and Chinese Treebank

MainPartExtractor. 主谓宾提取器的Java实现（对斯坦福的代码失去兴趣，不再维护）

ID-CNN-CWS. Source codes and corpora of paper "Iterated Dilated Convolutions for Chinese Word Segmentation"

neural_net. 反向传播神经网络及应用

udacity-deep-learning. Assignments for Udacity Deep Learning class with TensorFlow in PURE Python, not IPython Notebook

AveragedPerceptronPython. Clone of "A Good Part-of-Speech Tagger in about 200 Lines of Python" by Matthew Honnibal

text-classification-svm. The missing SVM-based text classification module implementing HanLP's interface

MaxEnt. 这是一个最大熵的简明Java实现，提供提供训练与预测接口。训练算法采用GIS训练算法，附带示例训练集和一个天气预测的Demo。

hidden-markov-model. First order HMM with Viterbi, Forward-Backward and Baum-Welch implementations

IceNAT. IceNAT

Coursera_NLP_MC. Coursera Natural Language Processing by Michael Collins Columbia University

BERT-token-level-embedding. Generate BERT token level embedding without pain

HanLPAndroidDemo. HanLP Android Demo

sub-character-cws. Sub-Character Representation Learning

coursera-neural-net. Assignments for Geoffrey Hinton's Neural Net Course on Coursera, translated from (gross)Matlab into (beautiful)Python.

maxent_iis. 最大熵-IIS（Improved Iterative Scaling）训练算法的Java实现

gohanlp. Golang RESTful Client for HanLP

iparser. Yet another dependency parser, integrated with tokenizer, tagger and visualization tool.

distributed-bert. TensorFlow code and pre-trained models for BERT

DeepBiaffineParserMXNet. An experimental implementation of biaffine parser using MXNet

chinese-corpus. 中文相关词典和语料库。

OpenCC-to-HanLP. 无损转换OpenCC词典为HanLP格式

libsvm. A Java Maven port of libsvm

RenrenAlbumDownloader. 人人网全部好友相册下载器

word2vec-lucene. This tool extracts word vectors from Lucene index.

word2vec. word2vec的Java并行实现

stanford_dl_ex. MATLAB

TextClassification. 文本分类

DeepLearning. Deep Learning (Python, C, C++, Java, Scala, Go)

gluon-nlp. NLP made easy

MA-FSA. This is a minimal acyclic finite-state automata algorithm in Java based on the paper, "Incremental Construction of Minimal Acyclic Finite-State Automata".

dsa-java. Data Structures and Algorithms in Java

sumy. Module for automatic summarization of text documents and HTML pages.

tmsvm. Python

datumbox-framework. Datumbox is an open-source Machine Learning framework written in Java which allows the rapid development of Machine Learning and Statistical applications.

Dictionaries. Java implementation of a DFA dictionary data structure