This repository is for me (and maybe for you) to understand a very simple NLP task: detecting if a given sentence is positive or negative. GloVe's pretrained word vectors are used. Both NumPy (main.py) and Keras (main2.py) are used. This has a very small training set, but pretrained vectors are sufficient to get a decent accuracy. GloVe vectors have several dimensions. More dimension means more accuracy in this case. Download GloVe from here (glove.6B.zip) and put it into data folder. I also put python file (mistakes.py) to see the examples from the test set that model misses. For this and your further Keras applications, I recommend using crestle.
kbulutozler/simple-sentence-analyzer
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
Analyzing sentences to detect if they are positive or negative. Based on Andrew Ng's 5th course of Deep Learning Specialization.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published