Natural Language Argumentation: Semantics, Pragmatics and Inference

Dear Colleagues,

In a world where communication shapes every facet of our lives, the study of semantics, pragmatics and inference in natural language argumentation is more crucial than ever. Understanding how we construct, interpret and infer meaning from arguments not only enhances our linguistic knowledge but also enriches applications in AI, law, education and quotidian discourse, whether on social media or elsewhere. Within natural language processing (NLP) research, critical questions about how we communicate and understand argumentation are both raised and addressed by empirical data-driven progress in semantics, pragmatics and natural language inference.

With recent advances in generative artificial intelligence and computational linguistics, we are armed with tools, frameworks and computational models that provide unprecedented opportunities to explore these complex phenomena and analyze complex structures of argumentation. These include formal models to represent and make a logical judgement about argumentation as well as the examination of argumentation in various domains such as legal documents, social media discourse, debates, product reviews and the scientific literature. Furthermore, we have significantly enhanced the capability of NLP to identify and apply rhetorical strategies, detect fallacious argumentation and evaluate the propriety and strength of arguments in various contexts.

Despite these advancements, there remain several critical avenues that warrant further exploration. One such path is the understanding of nuanced, context-dependent argumentation that requires a deep understanding of implicit meanings and cultural landscapes—thus, inevitably intersecting with natural language pragmatics and inference. For example, current models often fail to comprehend sarcasm, irony and other figurative uses of language in communication. There is also a need for better integration of ethical considerations and bias detection into argumentation systems to ensure that AI-generated argumentation is fair. Additionally, there remains significant scope for improvement in at least three orthogonal directions: (1) areas like argument summarization, argument structure tracing, reasoning about relations between arguments, and the incorporation of common sense knowledge into argumentation and reasoning, (2) inspections of the epistemology and typology of the information needed for computational modeling of argumentation, and (3) the intersection of morality and argumentation in human communication. Bridging these gaps remains a difficult and important challenge, as argumentation brings together cross-disciplinary perspectives from communication theory, philosophy, linguistics, psychology and computer science.

I am thus motivated to offer this Special Issue as a platform for researchers and practitioners to explore, discuss and present original research, novel insights, evaluations of data or methodologies, case studies and review articles related to the detection, categorization, assessment, reasoning and generation of arguments—or some aspects of it—in communication. I invite submissions pertinent to the above interests and encourage interdisciplinary approaches. The aim of this Special Issue is to foster collaboration and knowledge sharing among the machine learning, NLP, linguistics, psychology, AI and human–computer interaction communities, enabling complementary expertise to come together and push the boundaries of this prominent yet challenging area of natural language processing.

Topics relevant to the proposed Special Issue include, but are not limited to, the following:

• The extraction, identification, generation and categorization of natural language arguments.
• Formal models and representations of argumentation and reasoning.
• The role of semantics, pragmatics, inference and implicature in argumentation.
• Argument summarization and argument structure tracing.
• Common sense reasoning in argumentation.
• The robustness, correctness and relevance of arguments.
• Fallacious reasoning.
• Large language models (LLMs) in argumentation.
• Cultural perspectives and computational modeling of arguments.
• Modeling human behavior in argumentation.
• Benchmarking and evaluating data and models.
• The ethical, moral and social implications of AI in argumentation.
• Domain-specific applications.

Dr. Ritwik Banerjee
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Information is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• the extraction, identification, generation and categorization of natural language arguments
• formal models and representations of argumentation and reasoning
• the role of semantics, pragmatics, inference and implicature in argumentation
• argument summarization and argument structure tracing
• common sense reasoning in argumentation
• the robustness, correctness and relevance of arguments
• fallacious reasoning
• large language models (LLMs) in argumentation
• cultural perspectives and computational modeling of arguments
• modeling human behavior in argumentation
• benchmarking and evaluating data and models
• the ethical, moral and social implications of AI in argumentation
• domain-specific applications