Key Point Analysis via Contrastive Learning and Extractive Argument Summarization
This work addresses the problem of summarizing arguments for researchers and practitioners in argument mining, though it is incremental as it builds on existing shared task frameworks.
The paper tackled the task of extracting concise key points from argument collections by integrating contrastive learning for matching and graph-based extractive summarization for generation, achieving the best ranking in both automatic and manual evaluations in a shared task.
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, collocated 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.