- Preprocessing techniques like removing stopwords, punctuations, and contractions
- Custom word encoding and decoding using a Words class
- Attention mechanism implemented from scratch to capture important parts of the input sequence
- Achieved a train accuracy of 87% and validation accuracy of 88% on the Amazon Fine Food Reviews dataset
-
Notifications
You must be signed in to change notification settings - Fork 0
NilayGaitonde/Attention
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
Machine translation and Sentiment Analysis with the (scaled dot product) attention mechanism
Topics
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published