Context-Aware Interaction Network for Question Matching

Zhe Hu, Zuohui Fu, Yu Yin, Gerard de Melo


Abstract
Impressive milestones have been achieved in text matching by adopting a cross-attention mechanism to capture pertinent semantic connections between two sentence representations. However, regular cross-attention focuses on word-level links between the two input sequences, neglecting the importance of contextual information. We propose a context-aware interaction network (COIN) to properly align two sequences and infer their semantic relationship. Specifically, each interaction block includes (1) a context-aware cross-attention mechanism to effectively integrate contextual information when aligning two sequences, and (2) a gate fusion layer to flexibly interpolate aligned representations. We apply multiple stacked interaction blocks to produce alignments at different levels and gradually refine the attention results. Experiments on two question matching datasets and detailed analyses demonstrate the effectiveness of our model.
Anthology ID:
2021.emnlp-main.312
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3846–3853
Language:
URL:
https://aclanthology.org/2021.emnlp-main.312
DOI:
10.18653/v1/2021.emnlp-main.312
Bibkey:
Cite (ACL):
Zhe Hu, Zuohui Fu, Yu Yin, and Gerard de Melo. 2021. Context-Aware Interaction Network for Question Matching. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 3846–3853, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Context-Aware Interaction Network for Question Matching (Hu et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.312.pdf
Video:
 https://aclanthology.org/2021.emnlp-main.312.mp4