PITA: Prompting Task Interaction for Argumentation Mining

Argumentation mining (AM) aims to detect the arguments and their inherent relations from argumentative textual compositions. Prior methods are afflicted by a sequential feature decoding paradigm, wherein they initially address the features of argumentation components (ACs) for argumentative relation type classification (ACTC) subtask. Then, these features are amalgamated in pairs for argumentative relation identification (ARI) subtask. Finally, the AC pairs and ascertained pertinent relations are employed for argumentative relation type classification (ARTC) subtask. However, these methods merely rely on a shared encoder to implicitly capture the interactions of the three subtasks, which cannot explicitly and comprehensively model the inter-relationship among subtasks. In this paper, we propose a novel method PITA for PromptIng Task interAction to model the inter-relationships among the three subtasks within a generative framework. Specifically, we employ a dynamic prompt template to indicate all ACs and AC pairs in the three subtasks. Then, we construct an undirected heterogeneous graph to capture the various relationships within and between ACs and AC pairs. We apply the Relational Graph Convolutional Network (RGCN) on the graph and inject the task interaction information into the soft prompts with continuous representations. PITA jointly decodes all ACs and AC pairs using the prompt template with task interaction information, which thus explicitly and comprehensively harmonizes the information propagation across the three subtasks. Extensive experiments show PITA achieves state-of-the-art performances on two AM benchmarks.