迈向创造性语言生成:汉语幽默自动生成的探索  

Towards creative language generation: exploring Chinese humor generation

作　　者：谭红叶[1,2] 闫真 李茹[1,2] 敬毅民 Hongye TAN;Zhen YAN;Ru LI;Yimin JING(School of Computer and Information Technology,Shanxi University,Taiyuan 030006,China;Key Laboratory of Ministry of Education for Computation Intelligence and Chinese Information Processing of Shanxi University,Taiyuan 030006,China)

机构地区：[1]山西大学计算机与信息技术学院,太原030006 [2]计算智能与中文信息处理教育部重点实验室,太原030006

出　　处：《中国科学：信息科学》2018年第11期1497-1509,共13页Scientia Sinica(Informationis)

基　　金：国家自然科学基金(批准号:61673248;61772324);山西省"1331工程"重点学科建设计划资助项目

摘　　要：幽默生成是计算创造性任务之一,能够赋予计算机一定的个性化与创造性,而且可以提升用户体验.本文以笑话的生成进行汉语幽默生成的探索性研究.首先提出一个符合当前自然语言生成技术的笑话生成任务:给定笑话的主体部分,生成相应的笑点句.然后,尝试了基于经典编码器–解码器框架的方法与基于生成对抗网络的方法来完成该任务.为了克服编码器–解码器框架中对幽默特点没有建模的局限,本文在生成对抗网络方法中融入了歧义性、不一致性、语音相似性、普遍性等笑话属性特征来评价、指导笑话的生成.实验结果表明:在生成对抗网络方法中融入笑话属性特征后,系统输出构成笑话的比例提升6个百分点.尽管从总体来看系统自动生成的笑点句构成笑话的比例还偏低,但本文通过对幽默生成问题的研究探索,带动了对创造性语言生成问题的洞察与理解,标志着我们向创造性语言生成的探索迈进了一步.Humor generation is one of the tasks of computational creativity, which can not only make a computer creative and have a personality, but also improve user experiences. This paper explores the generation of Chinese jokes, the main form of humor. In particular, the following task is considered： given the setup of a joke, generate the corresponding punchline that is in line with current natural language generation technologies using one of two approaches. One is based on the encoder-decoder framework and lacks modeling of humor characters. The other is based on generative adversarial networks（GANs）, in which four characters（ambiguity, incongruity, phonetic similarity, and universality） are introduced into the reward function to evaluate the generated jokes and supervise the generator. Experimental results show that the GANs approach with joke character rewards obtains promising improvements compared to the encoder-decoder framework, namely, extra six percentage points on the ratio of jokes. While the performance is insufficient, as a first step towards creative language generation, the insights obtained in the exploration will help us in future research.

关 键 词：幽默生成  笑话生成  深度学习  编码器–解码器框架  生成对抗网络 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]