STMAP: A novel semantic text matching model augmented with embedding perturbations

Yanhao Wang, Baohua Zhang, Weikang Liu, Jiahao Cai, Huaping Zhang

Abstract: Highlights•Proposing Semantic Text Matching Model Augmented with Perturbations (STMAP).•Introducing a noise perturbation augmentation scheme based on Gaussian noise.•Proposing a multi-task adaptive optimization scheme.•STMAP demonstrates strong generalization capabilities.•STMAP model achieves state-of-the-art result and performs well under Few-shot scenes.