Current formal dialectical models postulate normative rules that enable discussants to conduct dialogical interactions without committing fallacies. Though the rules for conducting a dialogue are supposed to apply to interactions between actual arguers, they are without exception theoretically motivated. This creates a gap between model and reality, because dialogue participants typically leave important content-related elements implicit. Therefore, analysts cannot readily relate normative rules to actual debates in ways that will be empirically confirmable. This paper details a new, data-driven method for describing discussants’ actual reply structures, wherein corpus studies serve to acknowledge the complexity of natural argumentation (itself understood as a function of context). Rather than refer exclusively to propositional content as an indicator of arguing pro/contra a given claim, the proposed approach to dialogue structure tracks the sequence of dialogical moves itself. This arguably improves the applicability of theoretical dialectical models to empirical data, and thus advances the study of dialogue systems.

当前的正式辩证法模型假设了规范性规则，使讨论者能够进行对话互动而不会犯谬论。尽管进行对话的规则应该适用于实际辩论者之间的互动，但它们在理论上毫无例外地是出于动机。这在模型与现实之间造成了鸿沟，因为对话参与者通常将重要的与内容相关的元素保留为隐式。因此，分析人员不能轻易将规范性规则与实际辩论相关联，这在经验上是可以确认的。本文详细介绍了一种新的，数据驱动的方法，用于描述讨论者的实际答复结构，其中，语料库研究用于确认自然论证的复杂性（本身被理解为上下文的功能）。所提出的对话结构方法不仅跟踪命题内容作为争论给定权利要求的指标，还是跟踪对话动作本身的顺序。可以说这提高了理论辩证模型对经验数据的适用性，从而促进了对话系统的研究。