Looking at the Unseen: Effective Sampling of Non-Related Propositions for Argument Mining

Ramon Ruiz-Dolz (Lead / Corresponding author), Debela Gemechu, Zlata Kikteva, Chris Reed

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Downloads (Pure)

Abstract

Traditionally, argument mining research has approached the task of automatic identification of argument structures by using existing definitions of what constitutes an argument, while leaving the equally important matter of what does not qualify as an argument unaddressed. With the ability to distinguish between what is and what is not a natural language argument being at the core of argument mining as a field, it is interesting that no previous work has explored approaches to effectively select non-related propositions (i.e., propositions that are not connected through an argumentative relation, such as support or attack) that improve the data for learning argument mining tasks better. In this paper, we address the question of how to effectively sample non-related propositions from six different argument mining corpora belonging to different domains and encompassing both monologue and dialogue forms of argumentation. To that end, in addition to considering undersampling baselines from previous work, we propose three new sampling strategies relying on context (i.e., short/long) and the semantic similarity between propositions. Our results indicate that using more informed sampling strategies improves the performance, not only when evaluating models on their respective test splits, but also in the case of cross-domain evaluation.
Original languageEnglish
Title of host publicationProceedings of the 31st International Conference on Computational Linguistics
EditorsOwen Rambow, Leo Wanner, Marianna Apidianaki, Hend Al-Khalifa, Barbara Di Eugenio, Steven Schockaert
Place of PublicationAbu Dhabi, UAE
PublisherAssociation for Computational Linguistics
Pages2131-2143
Number of pages13
Publication statusPublished - Jan 2025

Fingerprint

Dive into the research topics of 'Looking at the Unseen: Effective Sampling of Non-Related Propositions for Argument Mining'. Together they form a unique fingerprint.

Cite this