Tony Veale’s research while affiliated with University College Dublin and other places

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.

The Cambridge Handbook of Irony and Thought offers the first comprehensive collection of chapters in multidisciplinary irony scholarship. These chapters explore the significance of irony, both verbal and situational, in language, thought, human action, and artistic expression. They cover five main themes: the scope of irony in human experience; irony's impact (both personal and in social life); irony in linguistic communication; irony and affect, and irony in expressive contexts. Contributions come from a wide range of academic disciplines, including psychology, linguistics, philosophy, literature, computer science, film and media studies, and music, making this a truly cross-disciplinary collection of benefit to a wide range of students and researchers.

Acting, stand-up and dancing are creative, embodied performances that nonetheless follow a script. Unless experimental or improvised, the performers draw their movements from much the same stock of embodied schemas. A slavish following of the script leaves no room for creativity, but active interpretation of the script does. It is the choices one makes, of words and actions, that make a performance creative. In this theory and hypothesis article, we present a framework for performance and interpretation within robotic storytelling. The performance framework is built upon movement theory, and defines a taxonomy of basic schematic movements and the most important gesture types. For the interpretation framework, we hypothesise that emotionally-grounded choices can inform acts of metaphor and blending, to elevate a scripted performance into a creative one. Theory and hypothesis are each grounded in empirical research, and aim to provide resources for other robotic studies of the creative use of movement and gestures.

Acting, stand-up and dancing are creative, embodied performances that nonetheless follow a script. Unless experimental or improvised, the performers draw their movements from much the same stock of embodied schemas. A slavish following of the script leaves no room for creativity, but active interpretation of the script does. It is the choices one makes, of words and actions, that make a performance creative. In this theory and hypothesis article, we present a framework for performance and interpretation within robotic storytelling. The performance framework is built upon movement theory, and defines a taxonomy of basic schematic movements and the most important gesture types. For the interpretation framework, we hypothesise that emotionally-grounded choices can inform acts of metaphor and blending, to elevate a scripted performance into a creative one. Theory and hypothesis are each grounded in empirical research, and aim to provide resources for other robotic studies of the creative use of movement and gestures.

We describe the design and implementation of a multi-modal storytelling system. Multiple robots narrate and act out an AI-generated story whose plots can be dynamically altered via non-verbal audience feedback. The enactment and interaction focuses on gestures and facial expression, which are embedded in a computational framework that draws on cognitive-linguistic insights to enrich the storytelling experience. With the absence of in-person user studies in this late breaking research, we present the validity of the separate modules of this project and introduce it to the HRI field.

Computers have enhanced productivity and cost-effectiveness in all of the creative industries, and their value as tools is rarely doubted. But can machines serve as more than mere tools, and assume the role and responsibilities of a co-creative partner, or even become goal-setting, autonomous creators in their own right? These are the questions that define the discipline of computational creativity. The answers require an algorithmic understanding of how humans give meaning to form, but a transformation in the way we think about creativity is unlikely to occur in a single bound. Rather, interdisciplinary insights from diverse fields must first inform our models, and shape a narrative of creativity in which machines are both tools and creators. To set the stage for the newest work, this introduction to the special issue on computational creativity shows where the field is going, and where it has come from.

To a human storyteller, a story is more than a textual artifact. Rather, as stories are both generated and generative, each is also a blueprint for performances to come. Tellers must draw on their own bodily affordances – from voice and gesture to movement around a stage – to bring stories to life, much as a conductor and an orchestra must translate a written score into actual music. This work explores the creative challenge of translating from a story-text to a story-performance, from words to physical actions and characters to embodied actors. The mapping requires distinct models for gesture, narration, orientation, dialogue and stage direction if computer-generated tales are to transcend the limitations of their production process. Using the Scéalability framework, we evaluate the interlocking role of spatial metaphor and pantomime in turning a narrative artifact into a coherent performance.

Stories are made to be told, yet the computational generation of stories has principally focused on stories as textual artifacts, rather than on the telling, or indeed the performance, of stories. The performative aspect of stories, in which a teller brings a tale to life, requires more than the written word. We humans use our bodies to enact a story, through the apt use of motion, space, timing and gesture. This work explores the physical enactment of computer-generated stories using multiple robots, which narrate the tale, and take on different roles of characters within it. They use pantomime to enhance the drama of narrative events, and use naturalistic gestures for more subtle communicative effects. They also use space as a mirror for abstract concerns such as affect and social relations. The paper outlines the Scéalability framework for turning story artifacts into performances, and presents empirical findings on the effectiveness of various embodied strategies. In particular, we show that audiences are sensitive to the coherent use of space in embodied story-telling, and appreciate the schematic use of spatial movements as much as more culturally specific pantomime gestures. For the presented study, we focus on one dimension of spatial movement involving two robot actors.