Towards Comprehensive Argument Analysis in Education: Dataset, Tasks, and Method
This work addresses the need for more detailed argument analysis in education, particularly for assessing argumentative writing, but it is incremental as it builds on existing argument mining methods with new annotations and tasks.
The paper tackled the problem of simplistic argument relations in argument mining by proposing 14 fine-grained relation types to capture complex structures, and conducted experiments on tasks like argument component detection and automated essay grading, showing the importance of these annotations for writing quality assessment.
Argument mining has garnered increasing attention over the years, with the recent advancement of Large Language Models (LLMs) further propelling this trend. However, current argument relations remain relatively simplistic and foundational, struggling to capture the full scope of argument information, particularly when it comes to representing complex argument structures in real-world scenarios. To address this limitation, we propose 14 fine-grained relation types from both vertical and horizontal dimensions, thereby capturing the intricate interplay between argument components for a thorough understanding of argument structure. On this basis, we conducted extensive experiments on three tasks: argument component detection, relation prediction, and automated essay grading. Additionally, we explored the impact of writing quality on argument component detection and relation prediction, as well as the connections between discourse relations and argumentative features. The findings highlight the importance of fine-grained argumentative annotations for argumentative writing quality assessment and encourage multi-dimensional argument analysis.