Recognizing Humour using Word Associations and Humour Anchor Extraction

This paper attempts to marry the interpretability of statistical machine learning approaches with the more robust models of joke structure and joke semantics capable of being learned by neural models. Specifically, we explore the use of semantic relatedness features based on word associations, rather than the more common Word2Vec similarity, on a binary humour identification task and identify several factors that make word associations a better fit for humour. We also explore the effects of using joke structure, in the form of humour anchors (Yang et al., 2015), for improving the performance of semantic features and show that, while an intriguing idea, humour anchors contain several pitfalls that can hurt performance.

[1]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[2]  Iryna Gurevych,et al.  SemEval-2017 Task 7: Detection and Interpretation of English Puns , 2017, *SEMEVAL.

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

[4]  Christiane Fellbaum,et al.  Book Reviews: WordNet: An Electronic Lexical Database , 1999, CL.

[5]  Xiaojuan Ma,et al.  Predicting Word Association Strengths , 2017, EMNLP.

[6]  Ted Pedersen,et al.  Extended Gloss Overlaps as a Measure of Semantic Relatedness , 2003, IJCAI.

[7]  Rada Mihalcea,et al.  Characterizing Humour: An Exploration of Features in Humorous Texts , 2009, CICLing.

[8]  Yoshihiko Hayashi Predicting the Evocation Relation between Lexicalized Concepts , 2016, COLING.

[9]  Ted Pedersen,et al.  Duluth at SemEval-2017 Task 6: Language Models in Humor Detection , 2017, SemEval@ACL.

[10]  Pascale Fung,et al.  Predicting humor response in dialogues from TV sitcoms , 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[11]  Catherine Havasi,et al.  Representing General Relational Knowledge in ConceptNet 5 , 2012, LREC.

[12]  Jan Snajder,et al.  TakeLab at SemEval-2017 Task 6: #RankingHumorIn4Pages , 2017, SemEval@ACL.

[13]  Jordan L. Boyd-Graber,et al.  Adding dense, weighted connections to WordNet , 2005 .

[14]  Anna Rumshisky,et al.  HumorHawk at SemEval-2017 Task 6: Mixing Meaning and Sound for Humor Recognition , 2017, SemEval@ACL.

[15]  Xiaojuan Ma,et al.  Effects of Semantic Relatedness between Setups and Punchlines in Twitter Hashtag Games , 2016, PEOPLES@COLING.

[16]  Victor Raskin,et al.  Semantic Theory of Humor , 1985 .

[17]  Thomas A. Schreiber,et al.  The University of South Florida free association, rhyme, and word fragment norms , 2004, Behavior research methods, instruments, & computers : a journal of the Psychonomic Society, Inc.

[18]  Kim Binsted,et al.  Machine humour : an implemented model of puns , 1996 .

[19]  Xiaojuan Ma Evocation: analyzing and propagating a semantic link based on free word association , 2013, Lang. Resour. Evaluation.

[20]  Hod Lipson,et al.  Humor as Circuits in Semantic Networks , 2012, ACL.

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

[22]  Kim Binsted,et al.  An Implemented Model of Punning Riddles , 1994, AAAI.

[23]  Gert Storms,et al.  Word associations: Norms for 1,424 Dutch words in a continuous task , 2008, Behavior research methods.

[24]  Anna Rumshisky,et al.  SemEval-2017 Task 6: #HashtagWars: Learning a Sense of Humor , 2017, *SEMEVAL.

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

[26]  C. Strapparava,et al.  HAHAcronym: Humorous Agents for Humorous Acronyms , 2003 .

[27]  Diyi Yang,et al.  Humor Recognition and Humor Anchor Extraction , 2015, EMNLP.

[28]  Pascale Fung,et al.  A Long Short-Term Memory Framework for Predicting Humor in Dialogues , 2016, NAACL.

[29]  Janyce Wiebe,et al.  Recognizing Contextual Polarity in Phrase-Level Sentiment Analysis , 2005, HLT.

[30]  Christian Federmann,et al.  Proceedings of the Tenth Workshop on Statistical Machine Translation, WMT@EMNLP 2015, 17-18 September 2015, Lisbon, Portugal , 2015, WMT@EMNLP.

[31]  Salvatore Attardo,et al.  Semantics and Pragmatics of Humor , 2008, Lang. Linguistics Compass.

[32]  Hinrich Schütze,et al.  AutoExtend: Extending Word Embeddings to Embeddings for Synsets and Lexemes , 2015, ACL.

[33]  Amy Perfors,et al.  Predicting human similarity judgments with distributional models: The value of word associations. , 2016, COLING.

[34]  Dragomir R. Radev,et al.  Humor in Collective Discourse: Unsupervised Funniness Detection in the New Yorker Cartoon Caption Contest , 2015, LREC.

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

[36]  Xiaojuan Ma,et al.  SRHR at SemEval-2017 Task 6: Word Associations for Humour Recognition , 2017, SemEval@ACL.