ViCLSR: A Supervised Contrastive Learning Framework with Natural Language Inference for Natural Language Understanding Tasks

ArXi:2603.21084v1 Announce Type: cross High-quality text representations are crucial for natural language understanding (NLU), but low-resource languages like Vietnamese face challenges due to limited annotated data. While pre-trained models like PhoBERT and CafeBERT perform well, their effectiveness is constrained by data scarcity. Contrastive learning (CL) has recently emerged as a promising approach for improving sentence representations, enabling models to effectively distinguish between semantically similar and dissimilar sentences.