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

Proceedings of NAACL-HLT 2016, pages 130–135, San Diego, California, June 12-17, 2016. c⃝2016 Association for Computational Linguistics A Long Short-Term Memory Framework for Predicting Humor in Dialogues Dario Bertero and Pascale Fung Human Language Technology Center Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Clear Water Bay, Hong Kong dbertero@connect.ust.hk, pascale@ece.ust.hk Abstract 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 au- dience would react. We model the setup- punchline relation of conversational humor with a Long Short-Term Memory, with utter- ance encodings obtained from a Convolutional Neural Network. Out neural network frame- work 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 un- derstand jokes. 1 Introduction There has been many recent attempts to detect and understand humor, irony and sarcasm from sen- tences, usually taken from Twitter (Reyes et al., 2013; Barbieri and Saggion, 2014; Riloff et al., 2013; Joshi et al., 2015), customer reviews (Reyes and Rosso, 2012) or generic canned jokes (Yang et al., 2015). Bamman and Smith (2015) and Karoui et al. (2015) included the surrounding context. Our work has a different focus from the above. We analyze transcripts of funny dialogues, a genre somehow neglected but important for human-robot interaction. Laughter is the natural reaction of peo- ple to a verbal or textual humorous stimulus. We want to predict when the audience would laugh. Compared to a typical canned joke or a sarcastic Tweet, a dialog utterance is perceived as funny only in relation to the dialog context and the past history. In a spontaneous setting a funny dialog is usually built through a setup which prepares the audience to receive the humorous discourse stimuli, followed by a punchline which releases the tension and triggers the laughter reaction (Attardo, 1997; Taylor and Ma- zlack, 2005). Automatic understanding of a humor- ous dialog is a first step to build an effective empa- thetic machine fully able to react to the user’s humor and to other discourse stimuli. We are ultimately in- terested in developing robots that can bond with hu- mans better (Devillers et al., 2015). As a source of situational humor we study a popu- lar TV sitcom: “The Big Bang Theory”. The domain of sitcoms is of interest as it provides a full dialog setting, together with an indication of when the au- dience is expected to laugh, given by the background canned laughters. An example of dialog from this sitcom, as well as of the setup-punchline schema, is shown below (punchlines in bold): PENNY: Okay, Sheldon, what can I get you? SHELDON: Alcohol. PENNY: Could you be a little more spe- …

Content truncated to 500 words