to-shimo Goto Github PK

alphaholdem

A Deep Reinforcment Learning Aproach to Texas Holdem

brown-cluster

C++ implementation of the Brown word clustering algorithm.

chinese-word2vec

word2vec/glove/swivel binary file on chinese corpus

cnn_sentence

CNNs for sentence classification

crf-shimo

A optimized version of crf++0.58 with a little faster and add some postprocess for chinese segment.

crfchunking-with-wordrepresentations

Train a CRF for syntactic chunking (CoNLL2000), and use word representations

cx-extractor

Automatically exported from code.google.com/p/cx-extractor

dict_build

自动构建中文词库：build dict from large chinese text using unsupervised method，algorithm：http://www.matrix67.com/blog/archives/5044

dl

flexse

mirror repository of flexse in google code. Author: [email protected]

gensim

Topic Modelling for Humans

glove

GloVe model for distributed word representation

guava

Google Core Libraries for Java 6+

hanlp

汉语言处理包 中文分词 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 简繁转换

ik-analyzer

Automatically exported from code.google.com/p/ik-analyzer

jsoncpp

A C++ library for interacting with JSON.

minicpm-v

MiniCPM-Llama3-V 2.5: A GPT-4V Level Multimodal LLM on Your Phone

mxnet

Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Go, Javascript and more

newspaper

News, full-text, and article metadata extraction in Python 3

online-coding-for-interview

在线协同编辑，用于远程面试写代码

resource_list

resource list about QA/NLP/NLG/DL/ML/Dialogue/IE/AI

sentence2vec

Tools for mapping a sentence with arbitrary length to vector space

tangshi-rnn

tidy-html5

The granddaddy of HTML tools, with support for modern standards

tiny-cnn

header only, dependency-free deep learning framework in C++11

topnews

头条新闻

utf8.h

📚 single header utf8 string functions for C and C++

word2vec

Multiple version of word2vec. https://code.google.com/p/word2vec/

word2vec-doc2vec

An extension of word2vec to efficiently represent new text as vectors. New text can be query, sentence and paragraph.

xgboost

Large-scale and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library, on single node, hadoop yarn and more.