DABERT: Dual Attention Enhanced BERT for Semantic Matching

Sirui Wang, Di Liang, Jian Song, Yuntao Li, Wei Wu


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.
Anthology ID:
2022.coling-1.141
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
1645–1654
Language:
URL:
https://aclanthology.org/2022.coling-1.141
DOI:
Bibkey:
Cite (ACL):
Sirui Wang, Di Liang, Jian Song, Yuntao Li, and Wei Wu. 2022. DABERT: Dual Attention Enhanced BERT for Semantic Matching. In Proceedings of the 29th International Conference on Computational Linguistics, pages 1645–1654, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
DABERT: Dual Attention Enhanced BERT for Semantic Matching (Wang et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.141.pdf
Data
GLUEQNLISICKSNLI