Skip to content

corlene-r/enhancing-bert-using-syntax

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

29 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Enhancing BERT Sentiment Classification using Syntactic Information

Authors: Alexander Peseckis, Corlene Rhoades, Ojas Sethi

This repository holds the code for our group's main project. Our project is titled 'Enhancing BERT Sentiment Classification Syntactic Information.'

To install the dependencies, run pip install -r requirements.txt from the main directory.

To train the model on the origional go-emotions dataset, run python main.py. To train it on the "ekman" dataset, run python main.py --taxonomy ekman, and to run it on the "group" dataset, run python main.py --taxonomy group.

You can also choose whether it uses the origional go-emotions model or our modified go-emotions model via the --model_type flag. By default, the modofied go-emotions model is used.

The syntax parser that we used was the Stanford Parser. It's not included in this repository because of file size constraints. However, the .jar file can be downloaded from this link: Stanford Parser. Some of the parsed trees are included in the data directory.

The paper and report for this experiment can be found in the repository with the file name report.pdf.

About

Course project for the CS 769 class at UW-Madison FA23

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%