Comments (2)
Hello, I see that you are also interested in the pre-trained vector, where the vector of ComplEx is in the form of real numbers, but I feel that it is in the form of complex numbers from the paper, I don't know if you understand why? Is it easy to answer?
from one-shot-relational-learning.
Hi , I have the same question, I am currently trying to recreate the pre-trained embedding for another dataset. Could you advise how was pre-trained embedding done? I used the base TransE model in OpenKE GitHub code (Discussed in the paper) to produce entity2vec.TransE but the format is not in the form of complexed numbers.
Could you share the code on how was pre-trained embedding produced?
from one-shot-relational-learning.
Related Issues (20)
- About experiment's result higher than that in paper HOT 3
- Low performance when testing with saved models
- About QueryEncoder.forward() HOT 1
- How to solve this problem?
- About dataset
- Incorrect relations in the training set
- the method of limiting the candidate entities HOT 1
- Figure1
- Pre-trained vectors on provided ComplEx
- Did you use MAML like method to train your model? HOT 3
- what is the“our model handles each example individually and ignores their interactions”in the paper
- How is file rel2candidates.json created HOT 4
- Dataset unavailable HOT 1
- Finding Wikipedia entities HOT 1
- entity candidate of Wiki data HOT 2
- About dataset download
- The url of data sets can't be connected, whatever way I tried. The address of nlp.cs.ucsb.edu is not available. Please change the download address HOT 3
- why do you use k steps of LSTM processor? HOT 1
- Invalid pre-trained embeddings download link HOT 3
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
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.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from one-shot-relational-learning.