Word2vec models (Mikolov et al.) focus on the learned hidden representation of the input. In this code, we try to treat behaviour as a language. We train a skip-gram model using Gensim to learn vector representations of the skills. Then we reduce their dimensionality using t-SNE and plot them to observe the clustering of skills.
-
Notifications
You must be signed in to change notification settings - Fork 2
rvoak/skill2vec
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
Skill clustering and analysis using word2vec by treating behavior as language.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published