tidalmelon

雨渐渐's repositories

addrseg

中文地址切分，及地址补全

Language:Python35 6 1

bigram

N-gram --bigram 二元分词（附人民日报语料库）

Language:C++700

LLM_case

GPT模型, langchain, prompt engineering, langchain, GPT工程化

Language:Jupyter Notebook200

perceptron

感知机

Language:C++200

autospider

自动化爬虫

Language:Python100

brpc-java

Java implementation for Baidu RPC, multi-protocol & high performance RPC.

Language:JavaApache-2.0100

me

最大熵模型

Language:Python100

ml_bayes

朴素贝叶斯---文本分类

Language:Java1 30

simpleseg

分词基本算法：逆向最大长度匹配

Language:Python100

ansj_seg

ansj分词.ict的真正java实现.分词效果速度都超过开源版的ict. 中文分词,人名识别,词性标注,用户自定义词典

Language:JavaApache-2.0000

ChineseSTS

中文文本语义相似度（Chinese Semantic Text Similarity）语料库建设

000

decision_tree

Language:Python000

exoskeleton_armor

chains: organize work flow

Language:Python000

FinGLM

000

fnlp

中文自然语言处理工具包 Toolkit for Chinese natural language processing (formerly FudanNLP)

Language:JavaLGPL-3.0000

HanLP

汉语言处理包分词词性标注命名实体识别依存句法分析关键词提取自动摘要短语提取拼音简繁 Lucene插件

Language:JavaApache-2.0000

incubator-brpc

Industrial-grade RPC framework used throughout Baidu, with 1,000,000+ instances and thousands kinds of services, called "baidu-rpc" inside Baidu.

Language:C++Apache-2.0000

Llama2-Chinese

Llama中文社区，最好的中文Llama大模型，完全开源可商用

000

lr

线性回归，逻辑回归

Language:Python000

miniseg

A Chinese Words Segmentation Tool Based on Bayes Model

Language:Python000

ml_hmm

隐马尔科夫模型---中文分词

Language:Python000

nlp-lang

这个项目是一个基本包.封装了大多数nlp项目中常用工具

Language:Java000

simhash

A Python Implementation of Simhash Algorithm

MIT000

similarity

similarity：相似度计算工具包，java编写。用于词语、短语、句子、词法分析、情感分析、语义分析等相关的相似度计算。

Language:JavaApache-2.0000

vim

a simple clone of ma6174/vim

Language:VimL000

wordnet

语义词典

Language:Python000

zkpython_example

A simple example using zkpython

Language:Python000