A Long Short-Term Memory Framework for Predicting Humor in Dialogues

We propose a first-ever attempt to employ a Long Short-Term memory based framework to predict humor in dialogues. We analyze data from a popular TV-sitcom, whose canned laughters give an indication of when the audience would react. We model the setuppunchline relation of conversational humor with a Long Short-Term Memory, with utterance encodings obtained from a Convolutional Neural Network. Out neural network framework is able to improve the F-score of 8% over a Conditional Random Field baseline. We show how the LSTM effectively models the setup-punchline relation reducing the number of false positives and increasing the recall. We aim to employ our humor prediction model to build effective empathetic machine able to understand jokes.

[1]  Ellen Riloff,et al.  Sarcasm as Contrast between a Positive Sentiment and Negative Situation , 2013, EMNLP.

[2]  RossoPaolo,et al.  A multidimensional approach for detecting irony in Twitter , 2013 .

[3]  Horacio Saggion,et al.  Modelling Irony in Twitter , 2014, EACL.

[4]  Julia M. Taylor,et al.  Toward Computational Recognition of Humorous Intent , 2005 .

[5]  George A. Miller,et al.  WordNet: A Lexical Database for English , 1995, HLT.

[6]  S. Attardo,et al.  The semantic foundations of cognitive theories of humor , 1997 .

[7]  Paolo Rosso,et al.  Making objective decisions from subjective data: Detecting irony in customer reviews , 2012, Decis. Support Syst..

[8]  Andrew McCallum,et al.  Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data , 2001, ICML.

[9]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[10]  Pascale Fung,et al.  Deep Learning of Audio and Language Features for Humor Prediction , 2016, LREC.

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

[12]  Jason Weston,et al.  Natural Language Processing (Almost) from Scratch , 2011, J. Mach. Learn. Res..

[13]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[14]  Guillaume Dubuisson Duplessis,et al.  Multimodal data collection of human-robot humorous interactions in the Joker project , 2015, 2015 International Conference on Affective Computing and Intelligent Interaction (ACII).

[15]  Geoffrey E. Hinton,et al.  Speech recognition with deep recurrent neural networks , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[16]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

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

[18]  Daniel Jurafsky,et al.  A Hierarchical Neural Autoencoder for Paragraphs and Documents , 2015, ACL.

[19]  Nathalie Aussenac-Gilles,et al.  Towards a Contextual Pragmatic Model to Detect Irony in Tweets , 2015, ACL.

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

[21]  Pushpak Bhattacharyya,et al.  Harnessing Context Incongruity for Sarcasm Detection , 2015, ACL.

[22]  Noah A. Smith,et al.  Transition-Based Dependency Parsing with Stack Long Short-Term Memory , 2015, ACL.

[23]  Hang Li,et al.  Neural Responding Machine for Short-Text Conversation , 2015, ACL.

[24]  Andrea Esuli,et al.  SENTIWORDNET: A Publicly Available Lexical Resource for Opinion Mining , 2006, LREC.

[25]  David Bamman,et al.  Contextualized Sarcasm Detection on Twitter , 2015, ICWSM.