Generative Data Augmentation for Improving Semantic Classification

We study sentence-level generative data augmentation for Bangla semantic classification across four public datasets and three pretrained model families (BanglaBERT, XLM-Indic, mBERT).We evaluate two widely used, reproducible techniquesparaphrasing (mT5-based) and round-trip backtranslation (BnEnBn)and analyze their impact under realistic class imbalance.Overall, augmentation often helps, but gains are tightly coupled to label quality: paraphrasing typically outperforms backtranslation and yields the most consistent improvements for the monolingual model, whereas multilingual encoders benefit less and can be more sensitive to noisy minority-class expansions.A key empirical observation is that the neutral class appears to be a major source of annotation noise, which degrades decision boundaries and can cap the benefits of augmentation even when positive/negative classes are clean and polarized.We provide practical guidance for Bangla sentiment pipelines: (i) use simple sentence-level augmentation to rebalance classes when labels are reliable; (ii) allocate additional curation and higher interannotator agreement targets to the neutral class.Our results indicate when augmentation helps and suggest that data qualitynot model choice alonecan become the limiting factor.