VLSP 2025 Shared Task: A Seq2Seq Transformer Approach to Vietnamese Semantic Parsing
Given limited computational resources, BARTpho and ViT5, two encoder–decoder transformer models are fine-tuned and the impact of tokenization strategies on transformer-based encoder–decoder models for Vietnamese semantic parsing is highlighted and promising directions for future research are suggested.
G. Huynh, T. Hà, T. Nguyen et al.
· 0 citations