ansj_fast_lda

LDA 的java实现

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

atlas

A powerful Android Dynamic Component Framework.

atnre

Adversarial Training for Neural Relation Extraction

cachematrix

chinesecodinginterviewappendix

The source code for the appendix part of the Chinese version of the book Coding Interviews

cnn-relation-extraction

Tensorflow Implementation of Convolutional Neural Network for Relation Extraction (NAACL 2015)

cnn-relationextraction

Convolution neural network for relation extraction between two given entities

cnschema

开放中文知识图谱的schema

cwe

datasciencecoursera

datasharing

The Leek group guide to data sharing

deepdive

DeepDive

deepnlp

Deep Learning NLP Pipeline implemented on Tensorflow

django-haystack

Modular search for Django

doc2vec_java

A Java implementation of doc2vec in ICML'14

entity_relation_extraction

基于依存分析的实体关系抽取简单实现，即抽取事实三元组

fact_triple_extraction

使用句法依存分析抽取事实三元组

fnlp

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

gensim

Topic Modelling for Humans

github

giza-pp

GIZA++ is a statistical machine translation toolkit that is used to train IBM Models 1-5 and an HMM word alignment model. This package also contains the source for the mkcls tool which generates the word classes necessary for training some of the alignment models.

hanlp

自然语言处理 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 新词发现 短语提取 自动摘要 文本分类 拼音简繁

haysearch

A movie search using haystack and whoosh

information-extraction-chinese

Chinese Named Entity Recognition with IDCNN/biLSTM+CRF, and Relation Extraction with biGRU+2ATT 中文实体识别与关系提取

jieba

结巴中文分词

languagecrunch

LanguageCrunch NLP server docker image

ltp

Language Technology Platform

ltp-cws

Chinese word segmentation module of LTP

mosesdecoder

Moses, the machine translation system