Explaining Arguments with Background Knowledge

Abstract

Most information we consume as a society is obtained over the Web. News-often from questionable sources-are spread online, as are election campaigns; calls for (collective) action spread with unforeseen speed and intensity. All such actions have argumentation at their core, and the conveyed content is often strategically selected or rhetorically framed. The responsibility of critical analysis of arguments is thus tacitly transferred to the content consumer who is often not prepared for the task, nor aware of the responsibility. The ExpLAIN project aims at making the structure and reasoning of arguments explicit-not only for humans, but for Robust Argumentation Machines that are endowed with language understanding capacity. Our vision is a system that is able to deeply analyze argumentative text: that identifies arguments and counter-arguments, and reveals their internal structure, conveyed content and reasoning. A particular challenge for such a system is to uncover implicit knowledge which many arguments rely on. This requires human background knowledge and reasoning capacity, in order to explicate the complete reasoning of an argument. This article presents ongoing research of the ExpLAIN project that aims to make the vision of such a system a tangible aim. We introduce the problems and challenges we need to address, and present the progress we achieved until now by applying advanced natural language and knowledge processing methods. Our approach puts particular focus on leveraging available sources of structured and unstructured background knowledge, the automatic extension of such knowledge, the uncovering of implicit content, and reasoning techniques suitable for informal, everyday argumentation.

Exploring Methodologies for Collecting High-Quality Implicit Reasoning in Arguments

“…While explication of warrants with assistance from teachers has been shown to be useful for improving students' argumentation skills, automating this explication process would not only help students to be less dependent on teachers, but it can also be beneficial for different downstream educational applications such as argument analysis (Becker et al, 2020), enthymeme reconstruction (Razuvayevskaya and Teufel, 2017;Hulpus et al, 2019) and essay scoring (Williamson, 2013). However, building an automated warrant explication system has been a challenge due to the difficulty of collecting warrants in a form that explicitly manifests the way a warrant relates the information between claim and premise.…”

“…Many previous work demonstrated different strategies of collecting high quality warrants (Becker et al, 2017;Habernal et al, 2018;Becker et al, 2020), but did not apply any restriction on the structure of warrants to handle the variety of reasoning patterns in which warrants can be explicated. In contrast, our annotation methodologies are designed to restrict the reasoning pattern and ensure that warrant explicates the reasoning link between claim and premise.…”

A Comparative Study on Collecting High-Quality Implicit Reasonings at a Large-scale

“…Re-constructing warrants in arguments can play an important role in many argument-related downstream applications, such as argumentative writing and comprehension support (Qin and Karabacak, 2010;von der Mühlen et al, 2019), improving students critical thinking (Hillocks, 2010), and debate systems (Weber et al, 2008). For some of these applications, assessing identification of warrants is an important step in developing a more complex pipeline for overall argument analysis (Becker et al, 2020). Furthermore, warrants can be leveraged to automatically give constructive feedback to users to assist them in the aforementioned argumentative applications.…”