Conference Papers Year : 2022

Double-Channel Multi-layer Information Fusion for Text Matching

Yongquan Dong
  • Function : Author
  • PersonId : 1275146

Abstract

Text matching is one of the fundamental tasks in natural language processing. Most of the existing models focus only on encoding the text itself but ignore other semantic information which may further improve matching accuracy. In this paper, we propose a novel model for text matching with double-channel multi-layer information fusion. It treats text and part-of-speech information of words in a sentence as double-channel information which is fused by multi-layer interactions. Meanwhile, our model uses a Siamese network structure to learn common and unique features of two sentences, which can improve its ability to learn the relationship between two sentences while reducing the parameter size and complexity. Experimental results on SNLI dataset show that our model can achieve better performance than baseline methods.
Fichier principal
Vignette du fichier
529309_1_En_10_Chapter.pdf (258.47 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04178723 , version 1 (08-08-2023)

Licence

Identifiers

Cite

Guoxi Zhang, Yongquan Dong, Huafeng Chen. Double-Channel Multi-layer Information Fusion for Text Matching. 12th International Conference on Intelligent Information Processing (IIP), May 2022, Qingdao, China. pp.114-123, ⟨10.1007/978-3-031-03948-5_10⟩. ⟨hal-04178723⟩
17 View
2 Download

Altmetric

Share

More