An audience’s prior beliefs and morals are strong indicators of how likely they will be affected by a given argument. Utilizing such knowledge can help focus on shared values to bring disagreeing parties towards agreement. In argumentation technology, however, this is barely exploited so far. This paper studies the feasibility of automatically generating morally framed arguments as well as their effect on different audiences. Following the moral foundation theory, we propose a system that effectively generates arguments focusing on different morals. In an in-depth user study, we ask liberals and conservatives to evaluate the impact of these arguments. Our results suggest that, particularly when prior beliefs are challenged, an audience becomes more affected by morally framed arguments.

In this work, we argue that augmenting argument generation technology with the ability to encode beliefs is of twofold. First, it gives more control on the generated arguments leading to better reach for audience. Second, it is one way of modeling the human process of synthesizing arguments. Therefore, we propose the task of belief-based claim generation, and study the research question of how to model and encode a user’s beliefs into a generated argumentative text. To this end, we model users’ beliefs via their stances on big issues, and extend state of the art text generation models with extra input reflecting user’s beliefs. Through an automatic evaluation we show empirical evidence of the applicability to encode beliefs into argumentative text. In our manual evaluation, we highlight that the low effectiveness of our approach stems from the noise produced by the automatic collection of bag-of-words, which was mitigated by removing this noise. The finding of this paper lays the ground work to further investigate the role of beliefs in generating better reaching arguments.

The premises of an argument give evidence or other reasons to support a conclusion. However, the amount of support required depends on the generality of a conclusion, the nature of the individual premises, and similar. An argument whose premises make its conclusion rationally worthy to be drawn is called sufficient in argument quality research. Previous work tackled sufficiency assessment as a standard text classification problem, not modeling the inherent relation of premises and conclusion. In this paper, we hypothesize that the conclusion of a sufficient argument can be generated from its premises. To study this hypothesis, we explore the potential of assessing sufficiency based on the output of large-scale pre-trained language models. Our best model variant achieves an F1-score of .885, outperforming the previous state-of-the-art and being on par with human experts. While manual evaluation reveals the quality of the generated conclusions, their impact remains low ultimately.

Key point analysis is the task of extracting a set of concise and high-level statements from a given collection of arguments, representing the gist of these arguments. This paper presents our proposed approach to the Key Point Analysis Shared Task, colocated with the 8th Workshop on Argument Mining. The approach integrates two complementary components. One component employs contrastive learning via a siamese neural network for matching arguments to key points; the other is a graph-based extractive summarization model for generating key points. In both automatic and manual evaluation, our approach was ranked best among all submissions to the shared task.