https://github.com/cooldragon12/model-multitask-learning

Implemented multitask learning in classifying the toxicity and emotion using Bi-LSTM with BERT
https://github.com/cooldragon12/model-multitask-learning

classification machine-learning multitask-learning nlp nlp-machine-learning

Last synced: 29 days ago
JSON representation

Implemented multitask learning in classifying the toxicity and emotion using Bi-LSTM with BERT

• Host: GitHub
• URL: https://github.com/cooldragon12/model-multitask-learning
• Owner: cooldragon12
• Created: 2023-11-28T06:02:02.000Z (11 months ago)
• Default Branch: main
• Last Pushed: 2024-06-21T13:52:19.000Z (5 months ago)
• Last Synced: 2024-06-22T06:29:22.029Z (5 months ago)
• Topics: classification, machine-learning, multitask-learning, nlp, nlp-machine-learning
• Language: Jupyter Notebook
• Homepage:
• Size: 4.88 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Multi-Task Learning for Emotion and Toxicity Classification in Valorant Chat using Bi-LSTM with Bert Embeddings

## Introduction

This repository contains the code for the training of the paper "ChattyTicket: Multi-Task Learning for Emotion and Toxicity Classification in Valorant Chat using Bi-LSTM" by: 

* [Johndel Encabo](www.linkedin.com/in/johndel-encabo) 

* Maria Cassandra Vitug

* Mark Kenneth Satsatin

## Requirements

* Python 3.9

* Tensorflow 2.5.0

* Keras 2.5.0

* Pandas 1.2.4

* Numpy 1.19.5

* Scikit-learn 0.24.2

* Matplotlib 3.4.2

Run the following command to install the required packages:

```

pip install -r requirements.txt

```

## Execution

To run the training with the default parameters, execute the following command:

```

python main.py -t | --train

```

This use the `default.ini` file as the configuration file. To use a different configuration file, use the `custom` flag:

```

python main.py custom -flags of the hyperparameter

```

To see the list of available flags, use the `--help` flag:

```

python main.py --help

```

To run the evaluation, use the `--eval` flag:

```

python main.py --eval | -e

```

For grid search, use the `--grid-search` flag:

```

python main.py --grid-search | -gs

```