###
计算机系统应用:2018,27(8):259-264
本文二维码信息
码上扫一扫!
基于递归神经网络的散文诗自动生成方法
姜力, 詹国华, 李志华
(杭州师范大学 信息科学与技术学院, 杭州 311121)
Automatic Generation Method of Prose Poem Based on Recurrent Neural Network
JIANG Li, ZHAN Guo-Hua, LI Zhi-Hua
(School of Information Science and Engineering, Hangzhou Normal University, Hangzhou 311121, China)
摘要
图/表
参考文献
相似文献
本文已被:浏览 281次   下载 158
投稿时间:2017-08-16    修订日期:2017-09-05
中文摘要: 针对中文散文诗歌的自动生成,提出一种基于循环神经网络的时序性文本生成方法.通过现有语料库构建好一个词语集后,首先给定若干关键词,在聚类模型生成的词语集基础上进行关键词扩展生成首句.在确定首句的基础上,利用上下文模型对已生成内容进行压缩和上文特征获取,最后将之前上下文内容传递给递归神经网络模型实现后续句子的生成.该方法中首句生成的过程利用语言模型中的词汇集扩展,并通过上下文模型获取关联实现上下句的映射关系.本文采用BLEU自动评测方式和人工评测方式,建立起较为标准的评测系统,实验结果证实了该方法的有效性.
Abstract:Aiming at the automatic generation of poem, a temporal text generation method using recurrent neural network is proposed. After building a word set according to the existing corpus, a number of keywords is given, and the first sentence is generated by expanding the keywords based on the word set constructed by clustering model. On the basis of the first sentence determined, the generated content is compressed by the context model and the feature is extracted, and finally the content of the previous context is passed to the generation model to realize the subsequent sentence generation. In order to achieve the mapping between the upper and lower sentences, the first sentence of the process is a vocabulary expansion, and the context model can be a good grasp of the context. BLEU automatic evaluation method and manual evaluation method are used to establish a more standard evaluation system. The results approve the effectiveness of the method.
文章编号:     中图分类号:    文献标志码:
基金项目:浙江省自然科学基金(LY17D060005)
引用文本:
姜力,詹国华,李志华.基于递归神经网络的散文诗自动生成方法.计算机系统应用,2018,27(8):259-264
JIANG Li,ZHAN Guo-Hua,LI Zhi-Hua.Automatic Generation Method of Prose Poem Based on Recurrent Neural Network.COMPUTER SYSTEMS APPLICATIONS,2018,27(8):259-264

用微信扫一扫

用微信扫一扫