Enhanced Sentence Alignment Network for Efficient Short Text Matching

Zhe Hu, Zuohui Fu, Cheng Peng, Weiwei Wang


Abstract
Cross-sentence attention has been widely applied in text matching, in which model learns the aligned information between two intermediate sequence representations to capture their semantic relationship. However, commonly the intermediate representations are generated solely based on the preceding layers and the models may suffer from error propagation and unstable matching, especially when multiple attention layers are used. In this paper, we pro-pose an enhanced sentence alignment network with simple gated feature augmentation, where the model is able to flexibly integrate both original word and contextual features to improve the cross-sentence attention. Moreover, our model is less complex with fewer parameters compared to many state-of-the-art structures.Experiments on three benchmark datasets validate our model capacity for text matching.
Anthology ID:
2020.wnut-1.6
Volume:
Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020)
Month:
November
Year:
2020
Address:
Online
Venues:
EMNLP | WNUT
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
34–40
Language:
URL:
https://aclanthology.org/2020.wnut-1.6
DOI:
10.18653/v1/2020.wnut-1.6
Bibkey:
Cite (ACL):
Zhe Hu, Zuohui Fu, Cheng Peng, and Weiwei Wang. 2020. Enhanced Sentence Alignment Network for Efficient Short Text Matching. In Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020), pages 34–40, Online. Association for Computational Linguistics.
Cite (Informal):
Enhanced Sentence Alignment Network for Efficient Short Text Matching (Hu et al., WNUT 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/2020.wnut-1.6.pdf
Optional supplementary material:
 2020.wnut-1.6.OptionalSupplementaryMaterial.zip
Data
MultiNLISNLI