Context-Driven Satirical News Generation

While mysterious, humor likely hinges on an interplay of entities, their relationships, and cultural connotations. Motivated by the importance of context in humor, we consider methods for constructing and leveraging contextual representations in generating humorous text. Specifically, we study the capacity of transformer-based architectures to generate funny satirical headlines, and show that both language models and summarization models can be fine-tuned to regularly generate headlines that people find funny. Furthermore, we find that summarization models uniquely support satire-generation by enabling the generation of topical humorous text. Outside of our formal study, we note that headlines generated by our model were accepted via a competitive process into a satirical newspaper, and one headline was ranked as high or better than 73% of human submissions. As part of our work, we contribute a dataset of over 15K satirical headlines paired with ranked contextual information from news articles and Wikipedia.

[1]  Victor Raskin,et al.  Semantic mechanisms of humor , 1984 .

[2]  V. Raskin,et al.  Script theory revis(it)ed: joke similarity and joke representation model , 1991 .

[3]  S. Attardo Humorous Texts: A Semantic and Pragmatic Analysis , 2001 .

[4]  N. Norrick Humor in Language , 2006 .

[5]  Rod A. Martin,et al.  The Psychology of Humor: An Integrative Approach , 2006 .

[6]  J. Shaw,et al.  Philosophy of Humor , 2010 .

[7]  Victor Raskin A Little Metatheory: Thought on What aTheory of Computational Humor Should Look Like , 2012, AAAI Fall Symposium: Artificial Intelligence of Humor.

[8]  Dafna Shahaf,et al.  Inside Jokes: Identifying Humorous Cartoon Captions , 2015, KDD.

[9]  Roger Levy,et al.  A Computational Model of Linguistic Humor in Puns , 2015, Cogn. Sci..

[10]  Bowen Zhou,et al.  Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond , 2016, CoNLL.

[11]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[12]  Mika Hämäläinen,et al.  A Master-Apprentice Approach to Automatic Creation of Culturally Satirical Movie Titles , 2018, INLG.

[13]  Xiaojun Wan,et al.  A Neural Approach to Pun Generation , 2018, ACL.

[14]  R'emi Louf,et al.  HuggingFace's Transformers: State-of-the-art Natural Language Processing , 2019, ArXiv.

[15]  Eric Horvitz,et al.  Reverse-Engineering Satire, or "Paper on Computational Humor Accepted Despite Making Serious Advances" , 2019, AAAI.

[16]  Nanyun Peng,et al.  Pun Generation with Surprise , 2019, NAACL-HLT.

[17]  Mirella Lapata,et al.  Text Summarization with Pretrained Encoders , 2019, EMNLP.

[18]  Michael Gamon,et al.  “President Vows to Cut Hair”: Dataset and Analysis of Creative Text Editing for Humorous Headlines , 2019, NAACL.

[19]  Ilya Sutskever,et al.  Language Models are Unsupervised Multitask Learners , 2019 .

[20]  Abhijit Mishra,et al.  A Modular Architecture for Unsupervised Sarcasm Generation , 2019, EMNLP.

[21]  Thomas Winters,et al.  Towards a General Framework for Humor Generation from Rated Examples , 2019, ICCC.

[22]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[23]  Ming-Wei Chang,et al.  REALM: Retrieval-Augmented Language Model Pre-Training , 2020, ICML.