SWAHILI TEXT CLASSIFICATION USING TRANSFORMERS

1

PyTorch

Let's dive into the main topic of this article, we are going to train a transformer model for Swahili news classification, Since transformers are large to make the task simple we need to select a wrapper to work with, if you are good with PyTorch you can use PyTorch Lightning a wrapper for high-performance AI research, to wrap the transformers but today lets go with ktrain from Tensorflow Python Library.

#Data Science And Machine Learning #Data Science Tools #AI 106 social mentions

2

Hugging Face

With the Transformer API in ktrain, we can select any Hugging Face transformers model appropriate for our data. Since we are dealing with Swahili, we will use multilingual BERT  which is normally used by ktrain for non-English datasets in the alternative text_classifier API in ktrain. But you can opt for any other multilingual transformer model.

#Social & Communications #Chatbots #AI 252 social mentions

3

Colaboratory

I recommend using google colab or kaggle kernel, in order to make the task simple and computational power from these platforms can make things go in a smooth way.

#Development #Education & Reference #Education 208 social mentions