Evaluating the Language of Argument

Hinton, Martin

doi:10.1007/978-3-030-61694-6

Cited by 16 publications

(15 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The evaluation which we conduct has as its theoretical background the principles expounded as the foundation to the CAPNA in Hinton [16]. These principles are the result of an attempt to mould the canon of argumentation theory into a shape which lends itself to the thorough and complete examination of argumentative texts, rather than the imposition of a revolutionary approach to argument.…”

Section: Hinton and Jhm Wagemans / How Persuasive Is Ai-generated Arg...mentioning

confidence: 99%

See 1 more Smart Citation

How persuasive is AI-generated argumentation? An analysis of the quality of an argumentative text produced by the GPT-3 AI text generator

Hinton

Wagemans

2023

AAC

Self Cite

View full text Add to dashboard Cite

In this paper, we use a pseudo-algorithmic procedure for assessing an AI-generated text. We apply the Comprehensive Assessment Procedure for Natural Argumentation (CAPNA) in evaluating the arguments produced by an Artificial Intelligence text generator, GPT-3, in an opinion piece written for the Guardian newspaper. The CAPNA examines instances of argumentation in three aspects: their Process, Reasoning and Expression. Initial Analysis is conducted using the Argument Type Identification Procedure (ATIP) to establish, firstly, that an argument is present and, secondly, its specific type in terms of the argument classification framework of the Periodic Table of Arguments (PTA). Procedural Questions are then used to test the acceptability of the argument in each of the three aspects. The analysis shows that while the arguments put forward by the AI text generator are varied in terms of their type and follow familiar patterns of human reasoning, they contain obvious weaknesses. From this we can conclude that the automated generation of persuasive, well-reasoned argumentation is a far more difficult task than the generation of meaningful language, and that if AI systems producing arguments are to be persuasive, they require a method of checking the plausibility of their own output.

show abstract

Section: Hinton and Jhm Wagemans / How Persuasive Is Ai-generated Arg...mentioning

confidence: 99%

“…The final stage of analysis is a close examination of the form of expression. This is done by checking the text for five qualities of language identified in the Informal Argument Semantics [15,16]: Clarity -language must not be vague. It must be clear enough for the purposes of the argument.…”

Section: Language Analysismentioning

confidence: 99%

How persuasive is AI-generated argumentation? An analysis of the quality of an argumentative text produced by the GPT-3 AI text generator

Hinton

Wagemans

2023

AAC

Self Cite

View full text Add to dashboard Cite

show abstract

“…To do the latter, we would need to work with a completely different set of understandings, one that involved the belief systems of fifth-century Athens and the assumptions of Platonic thought. This would be the minimal expectation if we wanted to evaluate argumentation from the perspective of Grice's theory of implicature (Hinton 2020;Moldovan 2012), let alone his theory of utterer's meaning. Krabbe's approach here illustrates that not all argumentation theorists will be particularly concerned by the problem that motivates this discussion.…”

Section: The Challenges Of the Cross-culturalmentioning

confidence: 99%

Utterer Meaning, Misunderstanding, and Cultural Knowledge

Tindale

2022

Languages

View full text Add to dashboard Cite

All versions of Grice’s theory of utterer meaning couch success in terms of stressing the hearer’s ability to recognize what is intended. This ties naturally to the cooperative principle and the maxims of conversation. A later additional maxim of manner emphasizes that one should always facility the audience’s response in one’s communication. Meaning communication is successful with the right “uptake”, whether seen in the desires or beliefs that Grice addressed in the audience, or the achievement of understanding or comprehension that critics identified. In retrospective reflections, Grice saw the latter necessitated by the former. The point remains that if Grice is correct in requiring audience recognition for the successful communication of meaning, then this poses serious challenges for scholars working in argumentation. It provides, for example, an additional problem when exploring cross-cultural argumentative exchanges where societies have had no prior experience of each other, their norms, or shared beliefs. Moreover, the conditions that it requires makes misunderstanding a central concern. These problems are explored in the paper, beginning with an initial assumption that Grice is correct about meaning, with a view to considering whether there is need for modifications to Grice’s theory.

show abstract

“…If the arguer is found to have committed neither a Process fallacy nor a Reasoning fallacy, then the final stage is the Language analysis which is conducted using the Informal Argument Semantics (IAS) developed and described at length Fig. 1 The Comprehensive Assessment Procedure for Natural Argumentation (CAPNA) (Hinton 2021: p. 169) in Hinton (2021). It should be reiterated at this point that IAS is a form of deep linguistic assessment designed to analyse and evaluate meaning at a level beyond what would be expected as a matter of course from a normally competent language user.…”

Section: Comprehensive Assessment Procedures For Natural Argumentationmentioning

confidence: 99%

“…This paper aims to contribute to the development of a less informal and comparative approach to argumentation assessment by providing a procedure for evaluating the underlying reasoning of individual arguments. It does so by combining insights from the Comprehensive Assessment Procedure for Natural Argumentation (CAPNA) set out in Hinton (2021) and the argument categorisation framework of the Periodic Table of Arguments (PTA) as presented in Wagemans (2016Wagemans ( , 2019Wagemans ( , 2020c. The combination of these two theoretical frameworks feeds a specification of the various steps of a procedure for the assessment of the reasoning aspect of individual arguments.…”

Section: Introductionmentioning

confidence: 99%

Evaluating Reasoning in Natural Arguments: A Procedural Approach

Hinton

Wagemans

2021

Argumentation

Self Cite

View full text Add to dashboard Cite

In this paper, we formulate a procedure for assessing reasoning as it is expressed in natural arguments. The procedure is a specification of one of the three aspects of argumentation assessment distinguished in the Comprehensive Assessment Procedure for Natural Argumentation (CAPNA) (Hinton, 2021) that makes use of the argument categorisation framework of the Periodic Table of Arguments (PTA) (Wagemans, 2016, 2019, 2020c). The theoretical framework and practical application of both the CAPNA and the PTA are described, as well as the evaluation procedure that combines the two. The procedure is illustrated through an evaluation of the reasoning of two example arguments from a recently published text.

show abstract

Evaluating the Language of Argument

Cited by 16 publications

References 0 publications

How persuasive is AI-generated argumentation? An analysis of the quality of an argumentative text produced by the GPT-3 AI text generator

How persuasive is AI-generated argumentation? An analysis of the quality of an argumentative text produced by the GPT-3 AI text generator

Utterer Meaning, Misunderstanding, and Cultural Knowledge

Evaluating Reasoning in Natural Arguments: A Procedural Approach

Contact Info

Product

Resources

About