For much of its history, AI was a scientific discipline defined more by its portrayal in science fiction than by its actual technical achievements. Real AI systems are now catching up to their fictional brethren, and are as likely to be seen in news headlines as on the big screen. Yet as AI systems match or even outperform people on tasks that were once considered yardsticks of human intelligence, one area of human experience still remains largely unchallenged by technology: our sense of humour. This is not for want of trying, as I will show. The true nature of humour has intrigued scholars for millennia, but AI researchers can go one step further than philosophers, linguists and psychologists once could: by building computer systems with a sense of humour, capable of appreciating the jokes of their human users or even of generating jokes of their own, we can turn academic theories into practical realities that amuse, explain, provoke and delight. This talk sets out to challenge the archetype of the rigidly humourless machine in popular culture, and to make a case for the necessity of a truly computational understanding of humour. By giving our machines the ability to understand and generate humour – including sarcasm and irony – we can better understand ourselves too, as we construct machines that are more flexible, more understanding, and more willing to laugh at their own limitations.

Metaphors are intriguing.We know that George Lakoff and Mark Johnson, in their book Metaphors We Live By, pointed out that our daily language is full of metaphors (Lakoff and Johnson 1980).Metaphors are not rare at all as linguistic events and in general as a means of human communication (e.g., in visual art).Thus, more than an exception, they seem to be a necessity for our mind.People use metaphors as strategies to link concepts, to deal with situations, and sometimes to suggest solutions to problems.For example, you can see criminality as a monster or as an illness.What you have in mind to deal with it is probably to fight in the former case, and to cure or to plan prevention in the latter.Nonetheless, metaphors are extremely difficult to model in a computational framework.What is literal?What is metaphorical?Making this distinction has often proved to be a daunting task, even for a human judgment.Metaphors-so bound to our way of thinking and entangled with a huge quantity of knowledge and linguistics subtletiesconstitute an excellent research problem for computational linguistics and artificial intelligence in general.We could probably say that they belong to the AI-complete problems.The difficulty of these computational problems is equivalent to that of solving the central artificial intelligence problem-making computers as intelligent as people.Tony Veale, Ekaterina Shutova, and Beata B. Klebanov are experienced researchers in the field of figurative language processing.Their book is an excellent resource and a good reference for anyone who plans to tackle the subtleties of this complex topic.The book offers a comprehensive approach to the computational treatment of metaphors and of related figurative devices such as simile, analogy, and conceptual blending.The reader is introduced to multiple computational perspectives, from symbolic and statistical approaches to interpretation and paraphrase generation, without omitting contributions from philosophy on what constitutes the significance of a metaphor.The first three chapters introduce the reader to the concept of metaphor, particularly the theoretical foundations profitable for approaching the problem computationally.Particularly useful is the explanation of the related figurative devices: similes (the comparison of one thing with another of a different kind, used to make a description more emphatic or vivid, e.g., John is as brave as a lion); analogy (a comparison between one thing and another, typically for the purpose of explanation, e.g., marriage is slavery); and conceptual blending (a cognitive theory, originally developed by Gilles Fauconnier and Mark Turner [Fauconnier and Turner 2002], which refers to a set of cognitive operations for combining-or blending-words, images, and ideas in a network of "mental spaces" to create meaning, e.g., the painting in George Clooney's attic is a cue to create a conceptual

Sarcasm is a pervasive phenomenon in social media, permitting the concise communication of meaning, affect and attitude.Concision requires wit to produce and wit to understand, which demands from each party knowledge of norms, context and a speaker's mindset.Insight into a speaker's psychological profile at the time of production is a valuable source of context for sarcasm detection.Using a neural architecture, we show significant gains in detection accuracy when knowledge of the speaker's mood at the time of production can be inferred.Our focus is on sarcasm detection on Twitter, and show that the mood exhibited by a speaker over tweets leading up to a new post is as useful a cue for sarcasm as the topical context of the post itself.The work opens the door to an empirical exploration not just of sarcasm in text but of the sarcastic state of mind.

Scripts are often dismissed as the stuff of good movies and bad politics. They codify cultural experience so rigidly that they remove our freedom of choice and become the very antithesis of creativity. Yet, mental scripts have an important role to play in our understanding of creative behaviour, since a deliberate departure from an established script can produce results that are simultaneously novel and familiar, especially when others stick to the conventional script. Indeed, creative opportunities often arise at the overlapping boundaries of two scripts that antagonistically compete to mentally organise the same situation. This work explores the computational integration of competing scripts to generate creative friction in short texts that are surprising but meaningful. Our exploration considers conventional macro-scripts – ordered sequences of actions – and the less obvious micro-scripts that operate at even the lowest levels of language. For the former, we generate plots that squeeze two scripts into a single mini-narrative; for the latter, we generate ironic descriptions that use conflicting scripts to highlight the speaker's pragmatic insincerity. We show experimentally that verbal irony requires both kinds of scripts – macro and micro – to work together to reliably generate creative sparks from a speaker's subversive intent.

One of the challenges of linguistic creativity is to use words in a way that is novel and striking and even whimsical, to convey meanings that remain stubbornly grounded in the very same world of familiar experiences as serves to anchor the most literal and unimaginative language. The challenge remains unmet by systems that merely shuttle or arrange words to achieve novel arrangements without concern as to how those arrangements are to spur the processes of meaning construction in a listener. In this paper we explore a problem of lexical invention that cannot be solved without a model – explicit or implicit – of the perceptual grounding of language: the invention of apt new names for colours. To solve this problem here we shall call upon the notion of a linguistic readymade, a phrase that is wrenched from its original context of use to be given new meaning and new resonance in new settings. To ensure that our linguistic readymades – which owe a great deal to Marcel Duchamp's notion of found art – are anchored in a consensus model of perception, we introduce the notion of a lexicalised colour stereotype.

Irony gives us a way to react creatively to disappointment. By allowing us to speak of a failed expectation as though it succeeded, irony stresses the naturalness of our expectation and the absurdity of its failure. The result of this playful use of language is a subtle valence shift as listeners are alerted to a gap between what is said and what is meant. But as irony is not without risks, speakers are often careful to signal an ironic intent with tone, body language, or if on Twitter, with the hashtag #irony. Yet given the subtlety of irony, we question the effectiveness of explicit marking, and empirically show how a stronger valence shift can be induced in automatically-generated creative tweets with more nuanced signals of irony.

Introspection is a question-led process in which one builds on what one already knows to explore what is possible and plausible. In creative introspection, whether in art or in science, framing the right question is as important as finding the right answer. Presupposition-laden questions are themselves a source of knowledge, and in this paper we show how widely-held beliefs about the world can be dynamically acquired by harvesting such questions from the Web. We show how metaphorical reasoning can be modeled as an introspective process, one that builds on questions harvested from the Web to pose further speculative questions and queries. Metaphor is much more than a knowledge-hungry rhetorical device: it is a conceptual lever that allows a system to extend its model of the world.

Irony is an effective but challenging mode of communication that allows a speaker to express sentiment-rich viewpoints with concision, sharpness and humour. Irony is especially common in online documents that express subjective and deeply-felt opinions, and thus represents a significant obstacle to the accurate analysis of sentiment in web texts. In this paper we look at one commonly used framing device for linguistic irony – the simile – to show how irony is often marked in ways that make it computationally feasible to detect. We conduct a very large corpus analysis of web-harvested similes to identify the most interesting characteristics of ironic comparisons, and provide an empirical evaluation of a new algorithm for separating ironic from non-ironic similes.

Language or word based casual games are becoming increasingly popular, but many of the game-play mechanics rely on spelling and word searching. This sub-genre of casual games is also targeted by serious games developers, but in their current 'spelling-bee' form they are not ideal tools for pedagogical assessment. Incorporating meta-data about linguistic constructs and their relationships would enable creative uses of existing corpora in games. Unfortunately, an impediment to integrating these linguistic resources into games is the laborious task of compiling and condensing the available data into a suitable form. This research into creative serious games has developed a word matching game which utilizes multiple diverse corpora to create the game-play data. The game itself is incorporated as an interface to an Intelligent Tutoring System framework. The design of the game and the approach to data generation is described.

An effective speaker can use metaphor to communicate a wealth of propositions and affective attitudes with a single juxtaposition of ideas [12,8,6,10,7,3,15]. But as such, an effective metaphor requires effective communication, which in turn requires that the speaker has a clear idea of the content to be communicated, and an equally clear understanding of which conceptual vehicles best communicate this content. We present here a concise corpusderived meaning representation for metaphor processing that captures the most widely-used talking points that are evoked in everyday metaphors and similes. We illustrate how these talking points can be acquired by harvesting the web, and further show how comparable but discretely different talking points can be reconciled during metaphor processing. Finally, by replicating the clustering experiments of [1], we show that talking points yield an especially concise representation of concepts in general.

Abstract Once viewed as a rhetorical and superficial language phenomenon, metaphor is now recognized to serve a fundamental role in our conceptual structuring and language comprehension processes. In particular, it is argued that certain experiential metaphors based upon intuitions of spatial relations are inherent in the conceptual organization of our most abstract thoughts. In this paper we present a two‐stage computational model of metaphor interpretation which employs a spatially founded semantics to broadly characterize the meaning carried by a metaphor in terms of a conceptual scaffolding, an interim meaning structure around which a fuller interpretation is fleshed out over time. We then present a semantics for the construction of conceptual scaffolding which is based upon core metaphors of collocation, containment and orientation. The goal of this scaffolding is to maintain the intended association of ideas even in contexts in which system knowledge is insufficient for a complete interpretation. This two‐stage system of scaffolding and elaboration also models the common time lapse between initial metaphor comprehension and full metaphor appreciation. Several mechanisms for deriving elaborative inference from scaffolding structures, particularly in cases of novel or creative metaphor, are also presented. While the system developed in this paper has significant practical application, it also demonstrates that core spatial metaphors clearly play a central role in metaphor comprehension.