Automatic Generation of Chinese Couplets with Attention Based Encoder-Decoder Model

被引:7
作者
Yuan, Shengqiong [1 ]
Zhong, Luo [1 ]
Li, Lin [1 ]
Zhang, Rui [1 ]
机构
[1] Wuhan Univ Technol, Sch Comp Sci & Technol, Wuhan, Hubei, Peoples R China
来源
2019 2ND IEEE CONFERENCE ON MULTIMEDIA INFORMATION PROCESSING AND RETRIEVAL (MIPR 2019) | 2019年
关键词
Deep learning; Recurrent Neural Network; attention; encoder-decoder; couplet;
D O I
10.1109/MIPR.2019.00020
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Chinese couplets, as one of the traditional Chinese culture, is the treasure of Chinese civilization and the inheritance of Chinese history. Given a sentence (namely an antecedent clause), people reply with another sentence (namely a subsequent clause) equal in length. Because of the complexity of the semantic and grammatical rules of couplet, it is not easy to create a suitable couplet that meets the requirements of sentence pattern, context, and flatness. In this paper, given the issued antecedent clause, we can automatically generate the subsequent clause by encoder-decoder model. Moreover, to satisfy special characteristics of couplets, we incorporate the attention mechanism into the encoding-decoding process, which greatly improves the accuracy of couplets generated automatically.
引用
收藏
页码:65 / 70
页数:6
相关论文
共 7 条
[1]  
Cho K., 2014, P SSST8 8 WORKSH SYN, P103, DOI 10.3115/v1/w14-4012
[2]  
Graves A, 2012, STUD COMPUT INTELL, V385, P1, DOI [10.1162/neco.1997.9.1.1, 10.1007/978-3-642-24797-2]
[3]  
He Jing, 2012, Proc. Twenty-Sixth AAAI Conf. Artif. Intell, P1650, DOI DOI 10.1609/AAAI.V26I1.8344
[4]  
Mikolov T, 2010, 11TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2010 (INTERSPEECH 2010), VOLS 1-2, P1045
[5]  
Yi Yong, 2005, MACHINE EVALUATION P
[6]  
Yue Fei, 1999, MULTILEVEL INTEGRATE
[7]  
[张开旭 ZHANG Kaixu], 2009, [中文信息学报, Journal of Chinese Information Processing], V23, P100