Dual Path Modeling for Semantic Matching by Perceiving Subtle Conflicts
This addresses the challenge of handling subtle word modifications in sentence pairs for semantic matching, though it appears incremental.
The paper tackles the problem of insufficient ability to capture subtle differences in semantic matching by proposing a Dual Path Modeling Framework, which achieves consistent improvements over baselines on 10 datasets.
Transformer-based pre-trained models have achieved great improvements in semantic matching. However, existing models still suffer from insufficient ability to capture subtle differences. The modification, addition and deletion of words in sentence pairs may make it difficult for the model to predict their relationship. To alleviate this problem, we propose a novel Dual Path Modeling Framework to enhance the model's ability to perceive subtle differences in sentence pairs by separately modeling affinity and difference semantics. Based on dual-path modeling framework we design the Dual Path Modeling Network (DPM-Net) to recognize semantic relations. And we conduct extensive experiments on 10 well-studied semantic matching and robustness test datasets, and the experimental results show that our proposed method achieves consistent improvements over baselines.