Publication
DFKI-MLST at DialAM-2024 Shared Task: System Description
Arne Björn Binder; Tatiana Anikina; Leonhard Hennig; Simon Ostermann
In: Yamen Ajjour; Roy Bar-Haim; Roxanne El Baff; Zhexiong Liu; Gabriella Skitalinskaya (Hrsg.). Proceedings of the 11th Workshop on Argument Mining (ArgMining 2024). ACL Workshop on Argument Mining (ArgMining-2024), located at The 62nd Annual Meeting of the Association for Computational Linguistics, August 15, Bangkok, Thailand, Pages 93-102, Association for Computational Linguistics, 2024.
Abstract
This paper presents the dfki-mlst submission for the DialAM shared task (Ruiz-Dolz et al., 2024) on identification of argumentative and illocutionary relations in dialogue. Our model achieves best results in the global setting: 48.25 F1 at the focused level when looking only at the related arguments/locutions and 67.05 F1 at the general level when evaluating the complete argument maps. We describe our implementation of the data pre-processing, relation encoding and classification, evaluating 11 different base models and performing experiments with, e.g., node text combination and data augmentation. Our source code is publicly available.