Tony Veale
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Tony Veale has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
Guofu Li
University College Dublin
3 shared publicationsAniruddha Ghosh
2 shared publications- Guofu Li
University College Dublin
2 shared publications - Pablo Gervás
Instituto de Tecnología del Conocimiento, Universidad Complutense de Madrid, 28040 Madrid, Spain
2 shared publications - Alessandro Valitutti
University College Dublin
1 shared publication - Alison Pease
University of Dundee
1 shared publication
Latest Publications
- 1 December 2023
- Published by Walter de Gruyter GmbH in Lodz Papers in Pragmatics
- Vol. 19 (2) , 385-414
“Somewhere along your pedigree, a bitch got over the wall!” A proposal of implicitly offensive language typology
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.
- 1 December 2023
- Published by Walter de Gruyter GmbH in Lodz Papers in Pragmatics
- Vol. 19 (2) , 385-414
“Somewhere along your pedigree, a bitch got over the wall!” A proposal of implicitly offensive language typology
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.
- Open Access
- 9 November 2020
- Published by Springer Nature in New Generation Computing
- Vol. 38 (4) , 551-563
Leaps and Bounds: An Introduction to the Field of Computational Creativity
- 9 November 2020
- Published by Springer Nature in New Generation Computing
- Vol. 38 (4) , 551-563
Open AccessLeaps and Bounds: An Introduction to the Field of Computational Creativity
- 1 February 2020
- Published by Walter de Gruyter GmbH in HUMOR
A unified theory of irony? As if ! Irony
- Open Access
SemEval-2013 Task 4: Free Paraphrases of Noun Compounds
In this paper, we describe SemEval-2013 Task 4: the definition, the data, the evaluation and the results. The task is to capture some of the meaning of English noun compounds via paraphrasing. Given a two-word noun compound, the participating system is asked to produce an explicitly ranked list of its free-form paraphrases. The list is automatically compared and evaluated against a similarly ranked list of paraphrases proposed by human annotators, recruited and managed through Amazon's Mechanical Turk. The comparison of raw paraphrases is sensitive to syntactic and morphological variation. The "gold" ranking is based on the relative popularity of paraphrases among annotators. To make the ranking more reliable, highly similar paraphrases are grouped, so as to downplay superficial differences in syntax and morphology. Three systems participated in the task. They all beat a simple baseline on one of the two evaluation measures, but not on both measures. This shows that the task is difficult.
Open AccessSemEval-2013 Task 4: Free Paraphrases of Noun Compounds
In this paper, we describe SemEval-2013 Task 4: the definition, the data, the evaluation and the results. The task is to capture some of the meaning of English noun compounds via paraphrasing. Given a two-word noun compound, the participating system is asked to produce an explicitly ranked list of its free-form paraphrases. The list is automatically compared and evaluated against a similarly ranked list of paraphrases proposed by human annotators, recruited and managed through Amazon's Mechanical Turk. The comparison of raw paraphrases is sensitive to syntactic and morphological variation. The "gold" ranking is based on the relative popularity of paraphrases among annotators. To make the ranking more reliable, highly similar paraphrases are grouped, so as to downplay superficial differences in syntax and morphology. Three systems participated in the task. They all beat a simple baseline on one of the two evaluation measures, but not on both measures. This shows that the task is difficult.
- 29 October 2019
- Published by Walter de Gruyter GmbH in HUMOR
- Vol. 33 (1)
A unified theory of irony? As if ! Irony, by Joana Garmendia
Article A unified theory of irony? As if ! Irony, by Joana Garmendia was published on February 1, 2020 in the journal HUMOR (volume 33, issue 1).
- 29 October 2019
- Published by Walter de Gruyter GmbH in HUMOR
- Vol. 33 (1)
A unified theory of irony? As if ! Irony, by Joana Garmendia
Article A unified theory of irony? As if ! Irony, by Joana Garmendia was published on February 1, 2020 in the journal HUMOR (volume 33, issue 1).
- 18 December 2018
- Published by Springer Nature in Annals of Mathematics and Artificial Intelligence
- Vol. 88 (5-6) , 439-456
Changing channels: divergent approaches to the creative streaming of texts
- 18 December 2018
- Published by Springer Nature in Annals of Mathematics and Artificial Intelligence
- Vol. 88 (5-6) , 439-456
Changing channels: divergent approaches to the creative streaming of texts
- 3 July 2018
- Published by Taylor & Francis in Metaphor and Symbol
- Vol. 33 (3) , 175-184
The “default” in our stars: Signposting non-defaultness in ironic discourse
A non-default interpretation is required whenever speakers creatively depart from established norms and defaults. But effective speakers do not travel alone when they move away from default meanings to novel, non-default destinations. Effective speakers bring their readers with them, sometimes by making the non-default destination the only meaningful destination that can be reached with an utterance, but other times by helpfully—if subtly—marking their utterances to facilitate the dislocation of words and meanings. We consider the relative utility of different indicators of non-defaultness in this article, ranging from the subtle to the overt. Our approach argues for the usefulness of machine-generated texts when quantitatively exploring aspects of human linguistic creativity, since machine-tooled utterances can better assure the consistency and comparability of novel utterances that are designed to offer strikingly original points of view. Within this mechanical framework, we measure the extent of the shift from default to non-default interpretations via the downshift from positive to negative affect in machine-generated ironic utterances. In using machine-generated texts, our approach and its results also argue for the possibility that intelligent machines can craft creative utterances of their own, and effectively communicate an ironic point-of-view to human readers.
- 3 July 2018
- Published by Taylor & Francis in Metaphor and Symbol
- Vol. 33 (3) , 175-184
The “default” in our stars: Signposting non-defaultness in ironic discourse
A non-default interpretation is required whenever speakers creatively depart from established norms and defaults. But effective speakers do not travel alone when they move away from default meanings to novel, non-default destinations. Effective speakers bring their readers with them, sometimes by making the non-default destination the only meaningful destination that can be reached with an utterance, but other times by helpfully—if subtly—marking their utterances to facilitate the dislocation of words and meanings. We consider the relative utility of different indicators of non-defaultness in this article, ranging from the subtle to the overt. Our approach argues for the usefulness of machine-generated texts when quantitatively exploring aspects of human linguistic creativity, since machine-tooled utterances can better assure the consistency and comparability of novel utterances that are designed to offer strikingly original points of view. Within this mechanical framework, we measure the extent of the shift from default to non-default interpretations via the downshift from positive to negative affect in machine-generated ironic utterances. In using machine-generated texts, our approach and its results also argue for the possibility that intelligent machines can craft creative utterances of their own, and effectively communicate an ironic point-of-view to human readers.
- 30 May 2018
- Published by Springer Nature
- p. 348-359
Plug and Play for a Transferrable Sense of Humour
- 12 October 2017
- Published by Springer Nature in Advances in Intelligent Systems and Computing
- p. 21-40
Metaphors of Creativity
- 12 October 2017
- Published by Springer Nature in Advances in Intelligent Systems and Computing
- p. 21-40
Metaphors of Creativity