From Arguments to Key Points: Towards Automatic Argument Summarization
This addresses the need for efficient argument summarization in domains like debate or content analysis, though it appears incremental as it builds on existing summarization concepts.
The paper tackles the problem of automatically summarizing large collections of arguments by representing them as a small set of scored key points, finding that a few key points cover most arguments and that experts can often predict them in advance.
Generating a concise summary from a large collection of arguments on a given topic is an intriguing yet understudied problem. We propose to represent such summaries as a small set of talking points, termed "key points", each scored according to its salience. We show, by analyzing a large dataset of crowd-contributed arguments, that a small number of key points per topic is typically sufficient for covering the vast majority of the arguments. Furthermore, we found that a domain expert can often predict these key points in advance. We study the task of argument-to-key point mapping, and introduce a novel large-scale dataset for this task. We report empirical results for an extensive set of experiments with this dataset, showing promising performance.