Comments (3)
@duhaime This is more so I can remember what's left for me to do. Feel free to add more if it helps you!
from lab-workshops.
Do we need to include any reference to the 2018 Mimno/Antoniak paper on stability, especially on small corpora, and to the (development branch only) support for word vectors in Mallet, which specifically include randomized bootstrap sampling which helps with this?
https://mimno.infosci.cornell.edu/info3350/readings/antoniak.pdf
https://github.com/mimno/Mallet/wiki/Word-Embeddings
Disregard if we are already mentioning or if not appropriate!
from lab-workshops.
We should totally add a link to the Mimno/Antoniak study. It provides a nice overview of the origins of randomness in embedding models and gives a nuanced response to the common question "how much data do I need to train an embedding model?" Good find!
from lab-workshops.
Related Issues (15)
- Suggested Workshop: Web Scraping Workshop HOT 2
- Using Github HOT 3
- Suggested workshop: find overrepresented terms
- Gathering a Building: Prototype
- Pull request tutorial HOT 2
- Palladio, per favore
- Building a Bookworm HOT 1
- Bookworm :: CGI Connection Error? HOT 9
- Bookworm on Ubuntu - /etc/mysql/my.cnf HOT 4
- Bookworm on Ubuntu - consider @locahost for MySQL permissions HOT 1
- D3 workshop HOT 1
- Would like command line github workshop HOT 1
- Interactive Plots Workshop HOT 2
- Word of thanks HOT 1
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 lab-workshops.