TY - CPAPER
KW - Attention mechanism
KW - Attention mechanisms
KW - Brain
KW - Classification (of information)
KW - Convolution
KW - convolutional neural network
KW - Convolutional neural networks
KW - Intangible cultural heritages
KW - Long short-term memory
KW - Long short-term memory network
KW - Memory network
KW - Semantic features
KW - Semantics
KW - Structural feature
KW - Text classification
KW - Text processing
KW - Traditional cultures
AU - Yang Xu
AU - Yuru Jiang
AU - Yu Wu
AU - Yuyao Zhang
AB - The couplet custom is one of China’s intangible cultural heritage, and it occupies a pivotal position in Chinese traditional culture. The general couplet requires that the first sentence and the second sentence be opposite and semantically coherent. As a particular type of couplets, Wu-Qing couplets are related on the character level but irrelevant at the sentence level. Such characteristics make the Wu-Qing couplet significantly different in structure and semantics compared to the general couplets. In this paper, Convolutional Neural Network is used to extract structural features. Long Short-Term Memory network and vector operations are used to extract semantic features, and the Attention mechanism is used to strengthen structural and semantic information. Finally, we propose a model with structural and semantic features between general couplets and Wu-Qing couplets. The final F1 score reached 82.6, which was an increase of 5.4 compared to the baseline model.
C1 - 21st Chinese Lexical Semantics Workshop, CLSW 2020
DO - 10.1007/978-3-030-81197-6_48
LA - English
N1 - Journal Abbreviation: Lect. Notes Comput. Sci. Pages: 575 Publication Title: Lect. Notes Comput. Sci.
N2 - The couplet custom is one of China’s intangible cultural heritage, and it occupies a pivotal position in Chinese traditional culture. The general couplet requires that the first sentence and the second sentence be opposite and semantically coherent. As a particular type of couplets, Wu-Qing couplets are related on the character level but irrelevant at the sentence level. Such characteristics make the Wu-Qing couplet significantly different in structure and semantics compared to the general couplets. In this paper, Convolutional Neural Network is used to extract structural features. Long Short-Term Memory network and vector operations are used to extract semantic features, and the Attention mechanism is used to strengthen structural and semantic information. Finally, we propose a model with structural and semantic features between general couplets and Wu-Qing couplets. The final F1 score reached 82.6, which was an increase of 5.4 compared to the baseline model.
PB - Springer Science and Business Media Deutschland GmbH
PY - 2021
SN - 03029743 (ISSN); 9783030811969 (ISBN)
SP - 562
EP - 575
TI - Classifying Wu-Qing Couplets and General Couplets with Structural and Semantic Features
UR - https://www.scopus.com/inward/record.uri?eid=2-s2.0-85139026338&doi=10.1007%2f978-3-030-81197-6_48&partnerID=40&md5=74a6158ace1dff7f54ed7cceb63561f0
VL - 12278 LNAI
ER -