An Empirical Study for Vietnamese Constituency Parsing with Pre-training
This is an incremental improvement for Vietnamese NLP, addressing parsing accuracy in a specific language domain.
The paper tackles Vietnamese constituency parsing using a span-based approach with pre-trained models, achieving F1-scores of 81.19% on VietTreebank and 85.70% on NIIVTB1 with XLM-Roberta.
In this work, we use a span-based approach for Vietnamese constituency parsing. Our method follows the self-attention encoder architecture and a chart decoder using a CKY-style inference algorithm. We present analyses of the experiment results of the comparison of our empirical method using pre-training models XLM-Roberta and PhoBERT on both Vietnamese datasets VietTreebank and NIIVTB1. The results show that our model with XLM-Roberta archived the significantly F1-score better than other pre-training models, VietTreebank at 81.19% and NIIVTB1 at 85.70%.