Graph Convolutional Network for Swahili News Classification
This addresses the problem of news classification for low-resourced African languages like Swahili in sparsely-labelled contexts, but it is incremental as it builds on existing Text GCN methods.
The paper tackles semi-supervised Swahili news classification by showing that Text Graph Convolutional Network (Text GCN) outperforms traditional NLP benchmarks, and introduces a variant using bag-of-words embeddings to reduce memory footprint while maintaining similar performance.
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.