Graph Convolutional Network for Swahili News Classification
arXiv:2103.09325
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.
arXiv comment8 pages, accepted at EACL AfricaNLP 2021
References in corpus (10)
- Distributed Representations of Sentences and Documents
- Longformer: The Long-Document Transformer
- Graph Neural Networks: A Review of Methods and Applications
- Deep Learning Based Text Classification: A Comprehensive Review
- XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization
- Big Bird: Transformers for Longer Sequences
- How to Fine-Tune BERT for Text Classification?
- Graph Convolutional Networks for Named Entity Recognition
- Masakhane -- Machine Translation For Africa
- From English To Foreign Languages: Transferring Pre-trained Language Models