hankcs repositories

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

Last commit Nov 24, 2021

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

Last commit Sep 3, 2016

Generate BERT token level embedding without pain

Last commit Feb 7, 2019

CRFSharp is Conditional Random Fields implemented by .NET(C#), a machine learning algorithm for learning from labeled sequences of examples.

Last commit Apr 23, 2015

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

Last commit Jun 23, 2018

Contest

Last commit Feb 9, 2015

Coursera Natural Language Processing by Michael Collins Columbia University

Last commit Mar 11, 2017

An experimental implementation of biaffine parser using MXNet

Last commit Sep 2, 2018

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

Last commit Oct 19, 2015

Java implementation of a DFA dictionary data structure

Last commit Apr 29, 2013

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

Last commit Oct 8, 2024

HanLP Android Demo

Last commit Aug 25, 2018

Source codes and corpora of paper "Iterated Dilated Convolutions for Chinese Word Segmentation"

Last commit Apr 15, 2021

IceNAT

Last commit Mar 8, 2015

A stand-alone Bloom filter implementation written in Java

Last commit Oct 10, 2011

A Java implemention of LDA(Latent Dirichlet Allocation)

Last commit Mar 24, 2017

Implementation of a large margin structured perceptron, including instances for sequence labeling, quotation extraction and dependency parsing.

Last commit Mar 28, 2014

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

Last commit Dec 20, 2014

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）

Last commit Oct 15, 2015

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。

Last commit Nov 23, 2014