Multi-Class-Text-Classification-BERT

Data Description

For our case study, we will be using the datasets from the hugging face library. The BERT model will be built on the AG News dataset.

• AG News (AG’s News Corpus) is a sub dataset of AG's corpus of news articles constructed by assembling titles and description fields of articles from the 4 largest classes
• The four classes are: World, Sports, Business, Sci/Tech
• The AG News contains 30,000 training and 1,900 test samples per class.

Aim

The project aims at building, training and fine tuning the BERT model with respect to classification on the AG News dataset.

Tech stack

• Language - Python
• Libraries – ktrain, transformers, datasets, numpy, pandas, tensorflow, timeit