基于生成对抗网络的事件描述生成

doi:10.11772/j.issn.1001-9081.2020081242

计算机应用 ›› 2021, Vol. 41 ›› Issue (5): 1256-1261.DOI: 10.11772/j.issn.1001-9081.2020081242

所属专题：人工智能

基于生成对抗网络的事件描述生成

孙鹤立¹, 孙玉柱^1,2, 张晓云¹

1. 西安交通大学计算机科学与技术学院, 西安 710049;
2. 西安交通大学外国语学院, 西安 710049

收稿日期:2020-08-18 修回日期:2020-10-14 出版日期:2021-05-10 发布日期:2020-12-09
通讯作者: 孙玉柱
作者简介:孙鹤立(1983-),女,辽宁铁岭人,副教授,博士,CCF会员,主要研究方向:数据挖掘、城市计算;孙玉柱(1982-),男,河北深州人,工程师,博士研究生,主要研究方向:数据挖掘、机器学习;张晓云(1996-),男,江苏苏州人,硕士研究生,主要研究方向:数据挖掘、机器学习。
基金资助:
国家自然科学基金资助项目（61672417）。

Event description generation based on generative adversarial network

SUN Heli¹, SUN Yuzhu^1,2, ZHANG Xiaoyun¹

1. School of Computer Science and Technology, Xi'an Jiaotong University, Xi'an Shaanxi 710049, China;
2. School of Foreign Studies, Xi'an Jiaotong University, Xi'an Shaanxi 710049, China

Received:2020-08-18 Revised:2020-10-14 Online:2021-05-10 Published:2020-12-09
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61672417).

摘要/Abstract

摘要： 在基于事件的社会网络（EBSN）中，自动生成社交事件（Social Event）的事件描述（Event Description）供组织者参考，从而有效避免描述贫乏、描述过度、精准度低的问题，易于形成丰富、准确、高吸引力的事件描述。为了自动生成与真实事件描述足够相似的文本，提出了一种生成对抗网络（GAN）模型GAN_PG来生成事件描述。GAN_PG模型中的生成模型（Generator）采用变分自编码器（VAE），判别模型（Discriminator）采用带门控循环单元（GRU）的神经网络。模型训练时借鉴了强化学习中的策略梯度（PG）下降，并通过设计合理的奖励函数来训练生成器生成事件描述。实验结果表明，设计的模型生成事件描述的BLEU-4值达到了0.67，证明了提出的事件描述生成模型GAN_PG可以无监督地产生与自然语言足够相似的事件描述。

关键词: 基于事件的社会网络, 事件描述, 文本生成, 生成对抗网络, 变分自编码器

Abstract: In Event-Based Social Networks (EBSNs), generating the event description of social events automatically is helpful for the organizer, so as to avoid the problems of poor description, descripting too much and low accuracy, and be easy to form rich, accurate and attractive event description. In order to automatically generate text that is sufficiently similar to true event description, a Generative Adversarial Network (GAN) model named GAN_PG was proposed to generate event description. In the GAN_PG model, the Variational Auto-Encoder (VAE) was used as the generator, and the neural network with the Gated Recurrent Unit (GRU) was used as the discriminator. In the model training, the Policy Gradient (PG) decline in reinforcement learning was used as reference, and a reasonable reward function was designed to train the generator to generate event description. Experimental results showed that the BLEU-4 value of the event description generated by GAN_PG reached 0.67, which proved that the event description generation model GAN_PG can generate event descriptions sufficiently similar to natural language in an unsupervised way.

Key words: Event-Based Social Network (EBSN), event description, text generation, Generative Adversarial Network (GAN), Variational Auto-Encoder (VAE)

中图分类号:

TP311

孙鹤立, 孙玉柱, 张晓云. 基于生成对抗网络的事件描述生成[J]. 计算机应用, 2021, 41(5): 1256-1261.

SUN Heli, SUN Yuzhu, ZHANG Xiaoyun. Event description generation based on generative adversarial network[J]. Journal of Computer Applications, 2021, 41(5): 1256-1261.

参考文献

[1] LIU X,HE Q,TIAN Y,et al. Event-based social networks:linking the online and offline social worlds[C]//Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York:ACM,2012:1032-1040.
[2] MIKOLOV T,KOMBRINGK S,DEORAS A,et al. RNNLM-recurrent neural network language modeling toolkit[C]//Proceedings of the 2011 IEEE Workshop on Automatic Speech Recognition and Understanding. Piscataway:IEEE,2011:1-4.
[3] KIM Y,JERNITE Y,SONTAG D,et al. Character-aware neural language models[C]//Proceedings of the 30th AAAI Conference on Artificial Intelligence. Palo Alto,CA:AAAI Press,2016:2741-2749.
[4] BOWMAN S R, VILNIS L, VINYALS O, et al. Generating sentences from a continuous space[C]//Proceedings of the 20th SIGNLL Conference on Computational Natural Language Learning. Stroudsburg,PA:Association for Computational Linguistics,2016:10-21.
[5] MUELLER J,GIFFORD D,JAAKKOLA T. Sequence to better sequence:continuous revision of combinatorial structures[C]//Proceedings of the 34th International Conference on Machine Learning. New York:JMLR. org,2017:2536-2544.
[6] 胡懋晗. 基于生成对抗网络的文本生成的研究[D]. 成都:电子科技大学,2020:2-7.(HU M H. Research on text generation based on generative adversarial network[D]. Chengdu:University of Electronic Science and Technology of China,2020:2-7.)
[7] YU L,ZHANG W,WANG J,et al. SeqGAN:sequence generative adversarial nets with policy gradient[C]//Proceedings of the 31st AAAI Conference on Artificial Intelligence. Palo Alto,CA:AAAI Press,2017:2741-2749.
[8] LIN K,LI D,HE X,et al. Adversarial ranking for language generation[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook,NY:Curran Associates Inc.,2017:3158-3168.
[9] 康云云, 彭敦陆, 陈章, 等. ED-GAN:基于改进生成对抗网络的法律文本生成模型[J]. 小型微型计算机系统,2019,40(5):1020-1025.(KANG Y Y,PENG D L,CHEN Z,et al. ED-GAN:judicial document generating model based on improved generative adversarial networks[J]. Journal of Chinese Computer Systems, 2019,40(5):1020-1025.)
[10] 喻鹏. 基于生成对抗网络的电子健康医疗数据生成[D]. 武汉:华中科技大学,2019:3-7.(YU P. GANs for electronic health record synthesis[D]. Wuhan:Huazhong University of Science and Technology,2019:3-7.)
[11] GOOFELLOW I J, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial nets[C]//Proceedings of the 27th International Conference on Neural Information Processing Systems. Cambridge:MIT Press,2014:2672-2680.
[12] 曹娟, 龚隽鹏, 张鹏洲. 数据到文本生成研究综述[J]. 计算机技术与发展,2019,29(1):80-84,89.(CAO J,GONG J P, ZHANG P Z. Review of data-to-text generation[J]. Computer Technology and Development,2019,29(1):80-84,89.)
[13] KINGMA D P,WELLING M. Auto-encoding variational Bayes[EB/OL].[2020-03-04]. https://arxiv.org/pdf/1312.6114.pdf.
[14] DOERSCH C. Tutorial on variational autoencoders[EB/OL].[2020-03-04]. https://arxiv.org/pdf/1606.05908.pdf.
[15] 杨云龙, 孙建强, 宋国超. 基于门控循环单元和胶囊特征的文本情感分析[J]. 计算机应用, 2020, 40(9):2531-2535. (YANG Y L, SUN J Q,SONG G C. Text sentiment analysis based on feature fusion of gated recurrent unit and capsule[J]. Journal of Computer Applications, 2020, 40(9):2531-2535.)
[16] 王根生, 黄学坚, 闵潞. 多元特征融合的GRU神经网络文本情感分类模型[J]. 小型微型计算机系统,2019,40(10):2130-2138.(WANG G S,HUANG X J,MIN L. GRU neural network text emotion classification model based on multi-feature fusion[J]. Journal of Chinese Computer Systems,2019,40(10):2130-2138.)
[17] PAPINENI K,ROULOS S,WARD T,et al. BLEU:a method for automatic evaluation of machine translation[C]//Proceedings of the 40th Annual Meeting on Association for Computational Linguistics. Stroudsburg, PA:Association for Computational Linguistics,2002:311-318.
[18] ETHAYARAJH K,SADIGH D. BLEU neighbors:a referenceless approach to automatic evaluation[EB/OL].[2020-03-05]. https://arxiv.org/pdf/2004.12726.pdf.

基于生成对抗网络的事件描述生成

Event description generation based on generative adversarial network

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	管其杰, 张挺, 李德亚, 周绍景, 杜奕. 基于多分辨率生成对抗网络的空间数据不确定性重建方法[J]. 计算机应用, 2021, 41(8): 2306-2311.
[2]	孙潇, 徐金东. 基于级联生成对抗网络的遥感图像去雾方法[J]. 计算机应用, 2021, 41(8): 2440-2444.
[3]	汤桂花, 孙磊, 毛秀青, 戴乐育, 胡永进. 基于深度对齐网络的生成对抗网络伪造人脸检测[J]. 计算机应用, 2021, 41(7): 1922-1927.
[4]	王先武, 张挺, 吉欣, 杜奕. 基于带梯度惩罚深度卷积生成对抗网络的页岩三维数字岩心重构方法[J]. 计算机应用, 2021, 41(6): 1805-1811.
[5]	李衍志, 范勇, 高琳. 基于形态流的石油钻井水流异常检测[J]. 计算机应用, 2021, 41(6): 1842-1848.
[6]	井贝贝, 郭嘉, 王丽清, 陈静, 丁洪伟. 结合降噪卷积神经网络和条件生成对抗网络的图像双重盲降噪算法[J]. 计算机应用, 2021, 41(6): 1767-1774.
[7]	郭茂祖, 杨倩楠, 赵玲玲. 基于条件Wassertein生成对抗网络的图像生成[J]. 计算机应用, 2021, 41(5): 1432-1437.
[8]	李雪晴, 王石, 王朱君, 朱俊武. 自然语言生成综述[J]. 计算机应用, 2021, 41(5): 1227-1235.
[9]	欧莉莉, 邵峰晶, 孙仁诚, 隋毅. 基于半监督方法的脑梗死图像识别[J]. 计算机应用, 2021, 41(4): 1221-1226.
[10]	段友祥, 张含笑, 孙歧峰, 孙友凯. 基于拉普拉斯金字塔生成对抗网络的图像超分辨率重建算法[J]. 计算机应用, 2021, 41(4): 1020-1026.
[11]	李虹霞, 秦品乐, 闫寒梅, 曾建潮, 鲍骞月, 柴锐. 基于面部特征图对称的人脸正面化生成对抗网络算法[J]. 计算机应用, 2021, 41(3): 714-720.
[12]	屠红艳, 张挺, 夏鹏飞, 杜奕. 基于改进型变分自编码器的不确定性空间信息重建方法[J]. 计算机应用, 2021, 41(10): 2959-2963.
[13]	张亚, 金鑫, 江倩, 李昕洁, 董云云, 姚绍文. 基于自动编码器的深度伪造图像检测方法[J]. 计算机应用, 2021, 41(10): 2985-2990.
[14]	黄晓祥, 胡咏梅, 吴丹, 任力杰. 基于变分自编码器的异常颈动脉早期识别和预测[J]. 计算机应用, 2021, 41(10): 3082-3088.
[15]	邱耀儒, 孙为军, 黄永慧, 唐瑜祺, 张浩川, 吴俊鹏. 基于生成对抗网络联合时空模型的行人重识别方法[J]. 计算机应用, 2020, 40(9): 2493-2498.