The automatic detection of implicitly offensive language is a challenge for NLP, as such language is subtle, contextual, and plausibly deniable, but it is becoming increasingly important with the wider use of large language models to generate human-quality texts. This study argues that current difficulties in detecting implicit offence are exacerbated by multiple factors: (a) inadequate definitions of implicit and explicit offense; (b) an insufficient typology of implicit offence; and (c) a dearth of detailed analysis of implicitly offensive linguistic data. (...) In this study, based on a qualitative analysis of an implicitly offensive dataset, a new typology of implicitly offensive language is proposed along with a detailed, example-led account of the new typology, an operational definition of implicitly offensive language, and a thorough analysis of the role of figurative language and humour in each type. Our analyses identify three main issues with previous datasets and typologies used in NLP approaches: (a) conflating content and form in the annotation; (b) treating figurativeness, particularly metaphor, as the main device of implicitness, while ignoring its equally important role in the explicit offence; and (c) an over-focus on form-specific datasets (e.g. focusing only on offensive comparisons), which fails to reflect the full complexity of offensive language use. (shrink)

Figure-Ground Duality in Humour: A Multi-Modal Perspective Creativity with words or pictures is not simply a matter of communicating a message, but of communicating it well, in a way that is effective, original and which defies convention. Effectiveness here pertains to the pragmatic goals of the communicator, and the extent to which these are achieved, while originality pertains to the manner in which the message is framed. Language, for instance, provides a wealth of conventions for framing a message; indeed, the (...) vast part of language is a solidified body of culturally received conventions, which fix the meaning of words and phrases and determine the contextual appropriateness of specific terms, topics and conversational strategies. To frame a message in a novel manner that stretches or even subverts these conventions, a communicator must imbue the elements of communication—whether words, gestures or pictorial elements—with additional meanings. This duality of meaning is not arbitrary, however, or communication cannot succeed. Rather, a creative communicator must draw out secondary meanings that are already implicit in the stock elements of communication, in a way that the audience can understand, appreciate and replicate. Duality thus lies at the heart of creative communication, allowing a communicator to say one thing and simultaneously convey another, secondary message that may augment or subvert the overt content of the communication. This mechanism, which draws out and gives prominence to that which is normally unseen or implicit, is Figure-Ground Reversal. (shrink)

Irony is an effective but challenging mode of communication that allows a speaker to express viewpoints rich in sentiment with concision, sharpness and humour. Creative 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 even the most creative uses of irony are often marked in (...) ways that make them 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. (shrink)

Computational Creativity: A Continuing Journey Content Type Journal Article DOI 10.1007/s11023-010-9212-0 Authors Tony Veale, Departamento de Ingeniera del Software e Inteligencia Artificial, Universidad Complutense de Madrid, Madrid, Spain Pablo Gervás, Departamento de Ingeniera del Software e Inteligencia Artificial, Universidad Complutense de Madrid, Madrid, Spain Rafael Pérez y Pérez, Departamento de Ingeniera del Software e Inteligencia Artificial, Universidad Complutense de Madrid, Madrid, Spain Journal Minds and Machines Online ISSN 1572-8641 Print ISSN 0924-6495 Journal Volume Volume 20 Journal Issue Volume 20, Number (...) 4. (shrink)