Conclusion-based Counter-Argument Generation

TL;DR

This paper introduces a method for automatic counter-argument generation that explicitly models the conclusion of the original argument and generates a counter with an opposing stance, improving relevance and stance adherence.

Contribution

It proposes a multitask learning approach that jointly generates conclusions and counters, incorporating stance-based ranking to enhance counter-argument relevance.

Findings

Generated counters are more relevant than baselines.

Counters better adhere to the opposing stance.

Approach outperforms existing methods in automatic and manual evaluations.

Abstract

In real-world debates, the most common way to counter an argument is to reason against its main point, that is, its conclusion. Existing work on the automatic generation of natural language counter-arguments does not address the relation to the conclusion, possibly because many arguments leave their conclusion implicit. In this paper, we hypothesize that the key to effective counter-argument generation is to explicitly model the argument's conclusion and to ensure that the stance of the generated counter is opposite to that conclusion. In particular, we propose a multitask approach that jointly learns to generate both the conclusion and the counter of an input argument. The approach employs a stance-based ranking component that selects the counter from a diverse set of generated candidates whose stance best opposes the generated conclusion. In both automatic and manual evaluation, we provide evidence that our approach generates more relevant and stance-adhering counters than strong baselines.