Tracing Humor in Edited News Headlines

Due to the diversity of language interpretation capacities, the computational natural language understanding (NLU) systems should be able to recognize semantic complex situations. In terms of natural language processing (NLP), computational humor detection is still one of the major challenges, having several applications, especially on social media. In order to observe how easily it is to create humor out of a serious title, in this paper, we aim at the development and comparison of machine learning and neural network models on the humor prediction task in news headlines, using the dataset provided by SemEval-2020. The experimental results demonstrate that the proposed approach is able to improve the humor detection performance, generated by applying short edits to headlines.

[1]  Ruli Manurung,et al.  Evaluating the STANDUP Pun Generating Software with Children with Cerebral Palsy , 2009, TACC.

[2]  Paolo Rosso,et al.  Irony Detection in a Multilingual Context , 2020, ECIR.

[3]  Tony Veale,et al.  Detecting Ironic Intent in Creative Comparisons , 2010, ECAI.

[4]  Ari Rappoport,et al.  Semi-Supervised Recognition of Sarcasm in Twitter and Amazon , 2010, CoNLL.

[5]  Giancarlo Salton,et al.  Representations of Idioms for Natural Language Processing: Idiom type and token identification, Language Modelling and Neural Machine Translation , 2017 .

[6]  Daniel Dor,et al.  On newspaper headlines as relevance optimizers , 2003 .

[7]  Horacio Saggion,et al.  Automatic Detection of Irony and Humour in Twitter , 2014, ICCC.

[8]  David Matthews,et al.  Unsupervised joke generation from big data , 2013, ACL.

[9]  Mikhail Khodak,et al.  A Large Self-Annotated Corpus for Sarcasm , 2017, LREC.

[10]  Ruli Manurung,et al.  The STANDUP Interactive Riddle Builder , 2006 .

[11]  Carlo Strapparava,et al.  Making Computers Laugh: Investigations in Automatic Humor Recognition , 2005, HLT.

[12]  Paolo Rosso,et al.  A multidimensional approach for detecting irony in Twitter , 2013, Lang. Resour. Evaluation.

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

[14]  Kevin Seppi,et al.  Humor Detection: A Transformer Gets the Last Laugh , 2019, EMNLP.

[15]  Ronaldo C. Prati,et al.  The Comprehension of Figurative Language: What Is the Influence of Irony and Sarcasm on NLP Techniques? , 2016, Sentiment Analysis and Ontology Engineering.

[16]  Pushpak Bhattacharyya,et al.  “When Numbers Matter!”: Detecting Sarcasm in Numerical Portions of Text , 2019, WASSA@NAACL-HLT.

[17]  Adilzhan Ismailov,et al.  Humor Analysis Based on Human Annotation Challenge at IberLEF 2019: First-place Solution , 2019, IberLEF@SEPLN.

[18]  Mário J. Silva,et al.  Clues for detecting irony in user-generated contents: oh...!! it's "so easy" ;-) , 2009, TSA@CIKM.

[19]  Pushpak Bhattacharyya,et al.  Automatic Sarcasm Detection , 2016, ACM Comput. Surv..

[20]  Yuriy Brun,et al.  That's What She Said: Double Entendre Identification , 2011, ACL.