Comments (2)
These names are given to different variants of model used here for paraphrase generation tasks.
ED represents use of encoder-decoder network used in model
L represents model is trained using Cross-entropy loss
P represents model is trained using pair-wise discriminator loss
LP represents both above are used for training
S represents sharing of parameters of encoder from encoder-decoder network and discriminator used for pair-wise discriminator loss
G represents use of discriminator to train decoder as generator using adversarial loss.
example :
EDLPS : encoder-decoder network with shared parameters of encoder and discriminator(module used for pair-wise discriminator loss) trained using both cross-entropy loss and pair-wise discriminator loss.
from pqg-pytorch.
Thanks very much for your detail explanation.
from pqg-pytorch.
Related Issues (8)
- pre-trained model? HOT 3
- wrong delimiter in quora_prepro.py HOT 2
- Default epoch number? HOT 1
- score.py file is missing? HOT 1
- Predict with new paraphrase examples HOT 3
- Use nn.NLLLoss instead of CrossEntropyLoss HOT 1
- Evaluate Code HOT 5
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 pqg-pytorch.