An attempt to make Back-Translation differentiable, using probability weighted embeddings for predicted translations in the nucleus of the predicted distribution over target language sentences.
License: MIT License
The dataset used is WMT-14 en-de .
See colab notebook
Learning from Explanations with Neural Execution Tree
We are currently using entire XLM to embed our target sequence in case of training on parallel data. On the other hand, during evaluation and mono-lingual training we only use the initial embedding layers of XLM to encode.
We could either use full XLM to embed target sequences while training(It won't take much time as we have moved over the need to calculate the embedding for each word in dictionary).
Or we could use only initial embeddings of XLM for target sequences while training on parallel data too.
What do you want to try first? Which one do you think will give better results? Or let's continue with this mismatch that is currently there?
We use k-nucleus sampling that is differentiable. Should we use this differentiable sampling while training on monolingual data too? Or use the currently implemented beam search only?
React
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
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
Django
The Web framework for perfectionists with deadlines.
Laravel
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.
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.
