Giter Club home page Giter Club logo

embedding's People

Contributors

bookmanhan avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar

embedding's Issues

Missing file

Hi @BookmanHan ,

When I tried to compile Embedding.cpp with this syntax: g++ Embedding.cpp -o TransG, I found this error:
Import.hpp:18:30: fatal error: boost/function.hpp: No such file or directory
#include <boost/function.hpp>

I could not find this function.hpp on your github, could you provide it?
Thank you.
Kem

想请教下关于f(h,t)的计算

hyperplane方法里面为什么f(h,t)的计算公式是这样的?

  • fabs(sum(abs(head - relation * head.t() * relation + gap - tail + relation * tail.t() * relation)) - orbit*orbit)
    这个与paper里的公式好像不一样? @BookmanHan

Datasets

Hi, the link of datasets can not be opened. How can I get the WN18 dataset corresponding to SSP paper ?

TransG

TransG 模型对FB15K数据集进行训练时,为什么达不到论文中所提到的效果,我的参数完全按照论文中的参数设定的,请问TransG类的其他参数如何设置?
我训练的效果如下:
这是left:
1:0.787124
2:0.883082
3:0.244106
4:0.565695
Raw.BestMEANS = 265.16
Raw.BestMRR = 0.205449
Raw.BestHITS = 0.411251
Filter.BestMEANS = 152.369
Filter.BestMRR= 0.331879
Filter.BestHITS = 0.548831
total = 59071

这是right:
1:0.76324
2:0.286448
3:0.902593
4:0.592057
Raw.BestMEANS = 194.49
Raw.BestMRR = 0.265348
Raw.BestHITS = 0.489513
Filter.BestMEANS = 122.189
Filter.BestMRR= 0.390626
Filter.BestHITS = 0.614701
total = 59071
与论文中的相差有点大。我的n_cluster = 20; step_before = 10,variance_bound = 0.01,sot = false, be_weight_normalized = true; @BookmanHan

Model.hpp C4716报错

你好,在运行代码的时候Model.hpp文件报错,两个基类都没有返回值,编译器报错,请问这种情况怎么处理呢?

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.