KNOWCOMP POKEMON Team at DialAM-2024: A Two-Stage Pipeline for Detecting Relations in Dialogical Argument Mining

TL;DR

This paper presents a two-stage pipeline for dialogical argument mining, successfully identifying argumentative and illocutionary relations, and achieving top rankings in the DialAM-2024 shared task.

Contribution

It introduces a novel two-stage pipeline with data augmentation and contextual information integration for improved relation detection in dialogical argument mining.

Findings

Ranked 1st in ARI Focused score

Achieved 4th in Global Focused score

Demonstrated effective relation detection in dialogical contexts

Abstract

Dialogical Argument Mining(DialAM) is an important branch of Argument Mining(AM). DialAM-2024 is a shared task focusing on dialogical argument mining, which requires us to identify argumentative relations and illocutionary relations among proposition nodes and locution nodes. To accomplish this, we propose a two-stage pipeline, which includes the Two-Step S-Node Prediction Model in Stage 1 and the YA-Node Prediction Model in Stage 2. We also augment the training data in both stages and introduce context in Stage 2. We successfully completed the task and achieved good results. Our team Pokemon ranked 1st in the ARI Focused score and 4th in the Global Focused score.