Graph Convolutional Network for Swahili News Classification

TL;DR

This paper demonstrates that Text GCN effectively classifies Swahili news in semi-supervised settings and introduces a memory-efficient variant using bag of words embeddings.

Contribution

It empirically shows Text GCN's superiority for low-resource language classification and proposes a memory-efficient model variant.

Findings

Text GCN outperforms traditional benchmarks in Swahili news classification.

A bag of words variant reduces memory usage with comparable accuracy.

Effective semi-supervised classification for low-resource languages.

Abstract

This work empirically demonstrates the ability of Text Graph Convolutional Network (Text GCN) to outperform traditional natural language processing benchmarks for the task of semi-supervised Swahili news classification. In particular, we focus our experimentation on the sparsely-labelled semi-supervised context which is representative of the practical constraints facing low-resourced African languages. We follow up on this result by introducing a variant of the Text GCN model which utilises a bag of words embedding rather than a naive one-hot encoding to reduce the memory footprint of Text GCN whilst demonstrating similar predictive performance.