An extremely fast implementation of Aho Corasick algorithm based on Double Array Trie.
(1.016 stars) (302 forks) (0 issues indexadas) (0 good first issues abertas)
Repositórios
Repositórios de hankcs
Clone of "A Good Part-of-Speech Tagger in about 200 Lines of Python" by Matthew Honnibal
(49 stars) (28 forks) (0 issues indexadas) (0 good first issues abertas)
Generate BERT token level embedding without pain
(27 stars) (5 forks) (0 issues indexadas) (0 good first issues abertas)
CRFSharp is Conditional Random Fields implemented by .NET(C#), a machine learning algorithm for learning from labeled sequences of examples.
(0 stars) (1 fork) (0 issues indexadas) (0 good first issues abertas)
hankcs/CS224nPython
CS224n: Natural Language Processing with Deep Learning Assignments Winter, 2017
(687 stars) (268 forks) (0 issues indexadas) (0 good first issues abertas)
Contest
(0 stars) (0 forks) (0 issues indexadas) (0 good first issues abertas)
hankcs/Coursera_NLP_MCJavaScript
Coursera Natural Language Processing by Michael Collins Columbia University
(29 stars) (8 forks) (0 issues indexadas) (0 good first issues abertas)
An experimental implementation of biaffine parser using MXNet
(10 stars) (1 fork) (0 issues indexadas) (0 good first issues abertas)
Deep Learning (Python, C, C++, Java, Scala, Go)
(2 stars) (2 forks) (0 issues indexadas) (0 good first issues abertas)
Java implementation of a DFA dictionary data structure
(1 star) (3 forks) (0 issues indexadas) (0 good first issues abertas)
hankcs/HanLPPython
中文分词 词性标注 命名实体识别 依存句法分析 成分句法分析 语义依存分析 语义角色标注 指代消解 风格转换 语义相似度 新词发现 关键词短语提取 自动摘要 文本分类聚类 拼音简繁转换 自然语言处理
(33.741 stars) (10.089 forks) (0 issues indexadas) (0 good first issues abertas)
HanLP Android Demo
(27 stars) (6 forks) (0 issues indexadas) (0 good first issues abertas)
hankcs/ID-CNN-CWSPython
Source codes and corpora of paper "Iterated Dilated Convolutions for Chinese Word Segmentation"
(132 stars) (37 forks) (0 issues indexadas) (0 good first issues abertas)
hankcs/IceNATJava
IceNAT
(33 stars) (33 forks) (0 issues indexadas) (0 good first issues abertas)
A stand-alone Bloom filter implementation written in Java
(0 stars) (2 forks) (0 issues indexadas) (0 good first issues abertas)
hankcs/LDA4jJava
A Java implemention of LDA(Latent Dirichlet Allocation)
(197 stars) (140 forks) (1 issue indexada) (1 good first issue aberta)
Implementation of a large margin structured perceptron, including instances for sequence labeling, quotation extraction and dependency parsing.
(0 stars) (1 fork) (0 issues indexadas) (0 good first issues abertas)
hankcs/MA-FSAJava
This is a minimal acyclic finite-state automata algorithm in Java based on the paper, "Incremental Construction of Minimal Acyclic Finite-State Automata".
(2 stars) (1 fork) (0 issues indexadas) (0 good first issues abertas)
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）
(141 stars) (84 forks) (0 issues indexadas) (0 good first issues abertas)
hankcs/MaxEntJava
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。
(44 stars) (31 forks) (0 issues indexadas) (0 good first issues abertas)