percent4 Goto Github PK
Name: Jclian
Type: User
Bio: 微信公众号:NLP奇幻之旅 知识星球:自然语言处理奇幻之旅 知乎:NLP奇幻之旅
Location: Shanghai
Name: Jclian
Type: User
Bio: 微信公众号:NLP奇幻之旅 知识星球:自然语言处理奇幻之旅 知乎:NLP奇幻之旅
Location: Shanghai
本项目使用Keras实现quasi Mul-BERT,在人物关系数据集上进行测试验证,其中quasi的意思为近似,因为Mul-BERT模型的论文还未发表,更多模型的细节还未知,因此为近似Mul-BERT。
本项目使用Keras实现R-BERT,在人物关系数据集上进行测试验证。
Use Roberta(English) pretrained model to finish multiple choice question answering task with RACE dataset.
Use English Roberta PLM to do text classification(TC) task with GLUE dataset: SST-2.
Keras模型训练实时可视化
本项目使用Keras实现Transformer模型来进行文本分类(中文、英文均支持)。
本项目用于展示三元组抽取后形成的知识图谱,包括几本小说的实体关系,以及README.md,介绍这方面的一篇文章。
notes about Neo4J learning
本项目采用Firefly模型训练框架,使用LLAMA-2模型对多项选择阅读理解任务(Multiple Choice MRC)进行微调,取得了显著的进步。
本项目用于文档问答,使用向量嵌入 + ES 做召回,使用Rerank模型作为精排,再使用LLM做文档问答,Web框架使用Flask。
Using LLM to evaluate MMLU dataset.
本项目使用大语言模型(LLM)进行开放领域三元组抽取。
使用LLM对人物关系进行分类,记录模型训练、部署及评估结果。
Using LSTM model to complete short document classification task.
利用ALBERT+机器学习算法进行文本分类。
MathOperation
利用2019年语言和智能比赛的数据和训练的模型,对开放的影视新闻进行三元组抽取,形成影视知识图谱。
multi-label-classification-4-event-type
Using PhantomJS and requests module in Python to download songs.
Using Spring Boot to listen music online.
Using Neo4j and Py2neo to demonstrate Chinese top 20 movies and their actor, visualized by graph.
This project is mainly to introduce some classical methods in Numeric Analysis using Python.
本项目介绍如何在离线环境安装Python第三方模块。
本项目用于演示如何使用SQLAlchemy来操作MySQL数据库,简单的CRUD操作。
使用pandas的25个技巧。
结合BERT+GRU+ATT模型,对自己收集的人物关系数据进行模型训练,用于人物关系抽取。
个人首页
my personal blog with github + hexo
使用Pyecharts绘制个人足迹地图。
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.