Conclusion-based Counter-Argument Generation
This addresses the challenge of generating effective counter-arguments in debates, which is incremental as it builds on existing work by focusing on conclusion modeling.
The paper tackled the problem of generating natural language counter-arguments by explicitly modeling an argument's conclusion and ensuring the counter opposes it, resulting in more relevant and stance-adhering counters as evidenced by automatic and manual evaluations.
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.