- approccio lstm
- utilizzare 2 mappe di ingresso per ogni sentence
- entrambe costanti: in-domain e wikipedia
- una costante (in-domain) e una trainable (random)
- una costante (in-domain) e una trainable (in-domain)
- max-pooling invece di somma
- risultati ufficiali con entrambi gli embeddings
-
Notifications
You must be signed in to change notification settings - Fork 0
lucascanna/deep-learning
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
No description, website, or topics provided.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published