Journal
INFORMATION PROCESSING & MANAGEMENT
Volume 61, Issue 1, Pages -Publisher
ELSEVIER SCI LTD
DOI: 10.1016/j.ipm.2023.103576
Keywords
Semantic text matching; Data augmentation; Embedding perturbations; Adaptive networks; Few-shot
Ask authors/readers for more resources
In this study, we propose a data augmentation-based semantic text matching model called STMAP. By using Gaussian noise and noise mask signal for data augmentation, as well as employing an adaptive optimization network for training target optimization, our model achieves good performance in few-shot learning and semantic deviation problems.
Semantic text matching models have achieved outstanding performance, but traditional methods may not solve Few-shot learning problems and data augmentation techniques could suffer from semantic deviation. To solve this problem, we propose STMAP, which is implemented from the perspective of data augmentation based on Gaussian noise and Noise Mask signal. We also employ an adaptive optimization network to dynamically optimize the several training targets generated by data augmentation. We evaluated our model on four English datasets: MRPC, SciTail, SICK, and RTE, with achieved scores of 90.3%, 94.2%, 88.9%, and 68.8%, respectively. Our model obtained state-of-the-art (SOTA) results on three of the English datasets. Furthermore, we assessed our approach on three Chinese datasets, and achieved an average improvement of 1.3% over the baseline model. Additionally, in the Few-shot learning experiment, our model outperformed the baseline performance by 5%, especially when the data volume was reduced by around 0.4. Our ablation experiments further validated the effectiveness of STMAP.2
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available