DeepAI AI Chat
Log In Sign Up

Argument Undermining: Counter-Argument Generation by Attacking Weak Premises

by   Milad Alshomary, et al.

Text generation has received a lot of attention in computational argumentation research as of recent. A particularly challenging task is the generation of counter-arguments. So far, approaches primarily focus on rebutting a given conclusion, yet other ways to counter an argument exist. In this work, we go beyond previous research by exploring argument undermining, that is, countering an argument by attacking one of its premises. We hypothesize that identifying the argument's weak premises is key to effective countering. Accordingly, we propose a pipeline approach that first assesses the premises' strength and then generates a counter-argument targeting the weak ones. On the one hand, both manual and automatic evaluation proves the importance of identifying weak premises in counter-argument generation. On the other hand, when considering correctness and content richness, human annotators favored our approach over state-of-the-art counter-argument generation.


page 1

page 2

page 3

page 4


Conclusion-based Counter-Argument Generation

In real-world debates, the most common way to counter an argument is to ...

Parsimonious Argument Annotations for Hate Speech Counter-narratives

We present an enrichment of the Hateval corpus of hate speech tweets (Ba...

Revisiting the Role of Similarity and Dissimilarity in Best Counter Argument Retrieval

This paper studies the task of best counter-argument retrieval given an ...

Argument Generation with Retrieval, Planning, and Realization

Automatic argument generation is an appealing but challenging task. In t...

Argumentative Text Generation in Economic Domain

The development of large and super-large language models, such as GPT-3,...

Rudolf Christoph Eucken at SemEval-2023 Task 4: An Ensemble Approach for Identifying Human Values from Arguments

The subtle human values we acquire through life experiences govern our t...

Towards Knowledge-Grounded Counter Narrative Generation for Hate Speech

Tackling online hatred using informed textual responses - called counter...