Neural Joke Generation
نویسندگان
چکیده
Humor generation is a very hard problem in the area of computational humor. In this paper, we present a joke generation model based on neural networks. The model can generate a short joke relevant to the topic that the user specifies. Inspired by the architecture of neural machine translation and neural image captioning, we use an encoder for representing user-provided topic information and an RNN decoder for joke generation. We trained the model by short jokes of Conan O’Brien with the help of POS Tagger. We evaluate the performance of our model by human ratings from five English speakers. In terms of the average score, our model outperforms a probabilistic model that puts words into slots in a fixed-structure sentence.
منابع مشابه
Temporo-parietal and fronto-parietal lobe contributions to theory of mind and executive control: an fMRI study of verbal jokes
'Getting a joke' always requires resolving an apparent incongruity, but the particular cognitive operations called upon vary depending on the nature of the joke itself. Previous research has identified the primary neural correlates of the cognitive and affective processes called upon to respond to humor generally, but little work has been done on the substrates underlying the distinct cognitive...
متن کاملComputer, Tell Me a Joke ... but Please Make it Funny: Computational Humor with Ontological Semantics
Computational humor is a subdiscipline of computational linguistics with applications in human computer interfaces, edutainment, affective computing, intelligent agents, and other areas. Based on ontological semantics, we develop the resources and algorithms the computer needs to understand and produce humor, in principle and on a detailed example. Our ultimate output will not be that of a toy ...
متن کاملUnsupervised joke generation from big data
Humor generation is a very hard problem. It is difficult to say exactly what makes a joke funny, and solving this problem algorithmically is assumed to require deep semantic understanding, as well as cultural and other contextual cues. We depart from previous work that tries to model this knowledge using ad-hoc manually created databases and labeled training examples. Instead we present a model...
متن کاملThe Frog Test: A Tool for Measuring Humor Theories' Validity and Humor Preferences
For over a century multiple theoretical accounts proposed different sets of necessary and sufficient conditions for distinguishing humorous from non-humorous stimuli. The theories ranged from Freud’s (1960/1905) expression of forbidden thoughts, superiority theories (e.g., Gruner, 2000), and benign violations (McGraw and Warren, 2010) to incongruity resolution (Suls, 1972), error detection (Hur...
متن کاملNeural Correlates of Sex/Gender Differences in Humor Processing for Different Joke Types
Humor operates through a variety of techniques, which first generate surprise and then amusement and laughter once the unexpected incongruity is resolved. As different types of jokes use different techniques, the corresponding humor processes also differ. The present study builds on the framework of the 'tri-component theory of humor,' which details the mechanisms involved in cognition (compreh...
متن کامل