Pinned Repositories
awesome-knowledge-graph-1
整理知识图谱相关学习资料
awesome-pretrained-chinese-nlp-models
Awesome Pretrained Chinese NLP Models，高质量中文预训练模型集合
clothing-dataset
Closing dataset, all classes
DeepLearning_Notes_CV
:notebook: tensorflow，keras、python、numpy、matplotlib、scikit-learn、python 图像处理等。
gnn_application
GNN Application
llms-peft-cook
Efficient Fine-tuning of Large Language Models”
recomend-spark-solr-scala-image-rest
推荐引擎前端rest服务,因使用Hbase作为Spark ALS模型，需安装Hbase,也可以使用solr实时在线推荐
spark_recomend
使用Spark的MLlib、Hbase作为模型、Hive作数据清洗的核心推荐引擎,在Spark on Yarn测试通过
zookeeper-master-slave-example
zookeeper_book
从Paxos到zookeeper (分布式一致性原理与实践)
wengbenjue's Repositories
wengbenjue/THUOCL
THUOCL（THU Open Chinese Lexicon）中文词库
wengbenjue/2018-CCF-BDCI-China-Unicom-Research-Institute-top2
2018-CCF大数据与计算智能大赛-面向电信行业存量用户的智能套餐个性化匹配模型联通赛-复赛第二名
wengbenjue/2018-CCL-UIIMCS
CCL2018中移在线客服领域用户意图分类冠军1st方案
wengbenjue/bert-Chinese-classification-task
bert中文分类实践
wengbenjue/BERT-Classification-Tutorial
wengbenjue/bert_sa
bert sentiment analysis tensorflow serving with RESTful API
wengbenjue/CausalityEventExtraction
Causality event extraction demo project including casual patterns and experiment on large scale corpus. 基于因果关系知识库的因果事件图谱实验项目，本项目罗列了因果显式表达的几种模式，基于这种模式和大规模语料，再经过融合等操作，可形成因果事件图谱。
wengbenjue/China_stock_announcement
该项目通过python脚本从巨潮网络的服务器获取**股市（sz,sh）的公告(上市公司和监管机构),把公告信息放到数据库，公告文件下载到本地，并支持网页查询和读取。
wengbenjue/Chinese-Word-Vectors
100+ Chinese Word Vectors 上百种预训练中文词向量
wengbenjue/chinese_chatbot_corpus
中文公开聊天语料库
wengbenjue/ConversationalRobotDesign
对话机器人（聊天机器人）设计思考
wengbenjue/e2e-coref-old
ene to end neural coreference resolution(forked from https://github.com/kentonl/e2e-coref and make some little change)
wengbenjue/EventTriplesExtraction
An experiment and demo-level tool for text information extraction (event-triples extraction), which can be a route to the event chain and topic graph, 基于依存句法与语义角色标注的事件三元组抽取，可用于文本理解如文档主题链，事件线等应用。
wengbenjue/GPF
GPF（Graph Processing Flow）：利用图神经网络处理问题的一般化流程
wengbenjue/LSTM-CNN-SUD
Hybrid biLSTM and CNN architecture for Sentence Unit Detection
wengbenjue/MedicalNamedEntityRecognition
Medical Named Entity Recognition implement using bi-directional lstm and crf model with char embedding.CCKS2017中文电子病例命名实体识别项目,主要实现使用了基于字向量的四层双向LSTM与CRF模型的网络.该项目提供了原始训练数据样本(一般醒目,出院情况,病史情况,病史特点,诊疗经过)与转换版本,训练脚本,预训练模型,可用于序列标注研究.把玩和PK使用.
wengbenjue/Name-Entity-Recognition
Lstm-crf,Lattice-CRF,bert-ner及近年ner相关论文follow
wengbenjue/PersonRelationKnowledgeGraph
ChinesePersonRelationGraph, person relationship extraction based on nlp methods.中文人物关系知识图谱项目,内容包括中文人物关系图谱构建,基于知识库的数据回标,基于远程监督与bootstrapping方法的人物关系抽取,基于知识图谱的知识问答等应用。
wengbenjue/Python-Deep-Learning-Projects
Python Deep Learning Projects, published by Packt
wengbenjue/QASystemOnMedicalKG
disease centered Medical knowledge graph and qa system。知识图谱构建，自动问答，基于kg的自动问答。以疾病为中心的一定规模医药领域知识图谱，并以该知识图谱完成自动问答与分析服务。
wengbenjue/rasa-ui
Rasa UI is a web application for the Rasa NLU backend
wengbenjue/rasa_bot
整理：基于Rasa-NLU和Rasa-Core的任务型ChatBot
wengbenjue/Speech-Emotion-Analyzer
The neural network model is capable of detecting five different male/female emotions from audio speeches. (Deep Learning, NLP, Python)
wengbenjue/stopwords
中文常用停用词表（哈工大停用词表、百度停用词表等）
wengbenjue/TextGrapher
Text Content Grapher based on keyinfo extraction by NLP method。输入一篇文档，将文档进行关键信息提取，进行结构化，并最终组织成图谱组织形式，形成对文章语义信息的图谱化展示。
wengbenjue/textrank_text_summarization
A tutorial for Automatic Text Summarization using TextRank algorithm.
wengbenjue/traprange
A Method to Extract Table Content in PDF Files (Java)
wengbenjue/Voice_Activity_Detector
A statistical model-based Voice Activity Detection
wengbenjue/weixin_crawler
高效微信公众号历史文章和阅读数据爬虫powered by scrapy
wengbenjue/WordMultiSenseDisambiguation
WordMultiSenseDisambiguation, chinese multi-wordsense disambiguation based on online bake knowledge base and semantic embedding similarity compute,基于百科知识库的中文词语多词义/义项获取与特定句子词语语义消歧.