Generating Poetry Title Based on Semantic Relevance with Convolutional Neural Network

2nd International Conference on Automation, Control and Robotics Engineering

工业技术;计算机科学;无线电电子学

Li, Z.^1 ; Niu, K.^1 ; He, Z.Q.^1

Key Laboratory of Universal Wireless Communications, Ministry of Education, Beijing University of Posts and Telecommunications, No.10 Xitucheng Road, Haidian District, Beijing, China^1

关键词: Convolutional neural network;    Convolutional Neural Networks (CNN);    Encoder-decoder;    Semantic relevance;    Text summarization;    Word segmentation;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/235/1/012007/pdf
DOI  :  10.1088/1757-899X/235/1/012007

来源: IOP

【 摘 要 】

Several approaches have been proposed to automatically generate Chinese classical poetry (CCP) in the past few years, but automatically generating the title of CCP is still a difficult problem. The difficulties are mainly reflected in two aspects. First, the words used in CCP are very different from modern Chinese words and there are no valid word segmentation tools. Second, the semantic relevance of characters in CCP not only exists in one sentence but also exists between the same positions of adjacent sentences, which is hard to grasp by the traditional text summarization models. In this paper, we propose an encoder-decoder model for generating the title of CCP. Our model encoder is a convolutional neural network (CNN) with two kinds of filters. To capture the commonly used words in one sentence, one kind of filters covers two characters horizontally at each step. The other covers two characters vertically at each step and can grasp the semantic relevance of characters between adjacent sentences. Experimental results show that our model is better than several other related models and can capture the semantic relevance of CCP more accurately.