Dépôts

Dépôts de hankcs

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

Dernier commit 24 nov. 2021

 (1 016 stars) (302 forks) (0 issues indexées) (0 good first issues ouvertes)

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

Dernier commit 3 sept. 2016

 (49 stars) (28 forks) (0 issues indexées) (0 good first issues ouvertes)

Generate BERT token level embedding without pain

Dernier commit 7 févr. 2019

 (27 stars) (5 forks) (0 issues indexées) (0 good first issues ouvertes)

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

Dernier commit 23 avr. 2015

 (0 stars) (1 fork) (0 issues indexées) (0 good first issues ouvertes)

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

Dernier commit 23 juin 2018

 (687 stars) (268 forks) (0 issues indexées) (0 good first issues ouvertes)

Contest

Dernier commit 9 févr. 2015

 (0 stars) (0 forks) (0 issues indexées) (0 good first issues ouvertes)

Coursera Natural Language Processing by Michael Collins Columbia University

Dernier commit 11 mars 2017

 (29 stars) (8 forks) (0 issues indexées) (0 good first issues ouvertes)

An experimental implementation of biaffine parser using MXNet

Dernier commit 2 sept. 2018

 (10 stars) (1 fork) (0 issues indexées) (0 good first issues ouvertes)

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

Dernier commit 19 oct. 2015

 (2 stars) (2 forks) (0 issues indexées) (0 good first issues ouvertes)

Java implementation of a DFA dictionary data structure

Dernier commit 29 avr. 2013

 (1 star) (3 forks) (0 issues indexées) (0 good first issues ouvertes)

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

Dernier commit 8 oct. 2024

 (33 741 stars) (10 089 forks) (0 issues indexées) (0 good first issues ouvertes)

HanLP Android Demo

Dernier commit 25 août 2018

 (27 stars) (6 forks) (0 issues indexées) (0 good first issues ouvertes)

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

Dernier commit 15 avr. 2021

 (132 stars) (37 forks) (0 issues indexées) (0 good first issues ouvertes)

IceNAT

Dernier commit 8 mars 2015

 (33 stars) (33 forks) (0 issues indexées) (0 good first issues ouvertes)

A stand-alone Bloom filter implementation written in Java

Dernier commit 10 oct. 2011

 (0 stars) (2 forks) (0 issues indexées) (0 good first issues ouvertes)

A Java implemention of LDA(Latent Dirichlet Allocation)

Dernier commit 24 mars 2017

 (197 stars) (140 forks) (1 issue indexée) (1 good first issue ouverte)

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

Dernier commit 28 mars 2014

 (0 stars) (1 fork) (0 issues indexées) (0 good first issues ouvertes)

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

Dernier commit 20 déc. 2014

 (2 stars) (1 fork) (0 issues indexées) (0 good first issues ouvertes)

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)

Dernier commit 15 oct. 2015

 (141 stars) (84 forks) (0 issues indexées) (0 good first issues ouvertes)

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。

Dernier commit 23 nov. 2014

 (44 stars) (31 forks) (0 issues indexées) (0 good first issues ouvertes)