Izindaba-Tindzaba: Machine learning news categorisation for Long and Short Text for isiZulu and Siswati
This work addresses the lack of resources for native South African languages in NLP, though it is incremental as it applies existing methods to new data.
The study tackled news topic classification for low-resource South African languages isiZulu and Siswati by creating annotated datasets and testing baseline models, finding that XGBoost, Logistic Regression, and LSTM with Word2vec embeddings performed best.
Local/Native South African languages are classified as low-resource languages. As such, it is essential to build the resources for these languages so that they can benefit from advances in the field of natural language processing. In this work, the focus was to create annotated news datasets for the isiZulu and Siswati native languages based on news topic classification tasks and present the findings from these baseline classification models. Due to the shortage of data for these native South African languages, the datasets that were created were augmented and oversampled to increase data size and overcome class classification imbalance. In total, four different classification models were used namely Logistic regression, Naive bayes, XGBoost and LSTM. These models were trained on three different word embeddings namely Bag-Of-Words, TFIDF and Word2vec. The results of this study showed that XGBoost, Logistic Regression and LSTM, trained from Word2vec performed better than the other combinations.