Share Email Print

Proceedings Paper • new

Text matching based on reconstructed color interaction image
Author(s): Haohao Nie; Tanfeng Sun; Xinghao Jiang; Ke Xu
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Plenty of natural language processing tasks can be modeled as text matching, such as question answering, machine translation and so on. An elementary and efficacious method is to distill matching patterns from words, phrases and sentences to obtain the matching score. In this paper, Reconstructed Color Interaction Image (RCII) is proposed to convert text matching to color image recognition. First, two texts are reconstructed and similarity operations are adopted to generate Color Interaction Image (CII). Then CNN is applied to extract hierarchical and elaborate matching information. Finally, fully connected layers are employed to obtain the matching score. Experiments have proved the effectiveness of our method.

Paper Details

Date Published: 31 December 2019
PDF: 8 pages
Proc. SPIE 11384, Eleventh International Conference on Signal Processing Systems, 1138417 (31 December 2019); doi: 10.1117/12.2559552
Show Author Affiliations
Haohao Nie, Shanghai Jiao Tong Univ. (China)
Tanfeng Sun, Shanghai Jiao Tong Univ. (China)
Xinghao Jiang, Shanghai Jiao Tong Univ. (China)
Ke Xu, Shanghai Jiao Tong Univ. (China)

Published in SPIE Proceedings Vol. 11384:
Eleventh International Conference on Signal Processing Systems
Kezhi Mao, Editor(s)

© SPIE. Terms of Use
Back to Top