DABERT: Dual Attention Enhanced BERT for Semantic Matching

TL;DR

DABERT introduces a dual attention mechanism to enhance BERT's ability to detect subtle differences in sentence pairs, improving semantic matching accuracy and robustness.

Contribution

The paper proposes DABERT, a novel model with dual attention and adaptive fusion modules, to better capture fine-grained sentence differences compared to existing models.

Findings

DABERT outperforms baseline models on semantic matching datasets.

DABERT demonstrates improved robustness against sentence perturbations.

The dual attention mechanism effectively captures subtle semantic differences.

Abstract

Transformer-based pre-trained language models such as BERT have achieved remarkable results in Semantic Sentence Matching. However, existing models still suffer from insufficient ability to capture subtle differences. Minor noise like word addition, deletion, and modification of sentences may cause flipped predictions. To alleviate this problem, we propose a novel Dual Attention Enhanced BERT (DABERT) to enhance the ability of BERT to capture fine-grained differences in sentence pairs. DABERT comprises (1) Dual Attention module, which measures soft word matches by introducing a new dual channel alignment mechanism to model affinity and difference attention. (2) Adaptive Fusion module, this module uses attention to learn the aggregation of difference and affinity features, and generates a vector describing the matching details of sentence pairs. We conduct extensive experiments on well-studied semantic matching and robustness test datasets, and the experimental results show the effectiveness of our proposed method.