Dataset independent baselines for relation prediction in argument mining

Oana Cocarascu, Elena Cabrio, Serena Villata, Francesca Toni

Research output: Chapter in Book/Report/Conference proceedingConference paperpeer-review

10 Citations (Scopus)


Argument(ation) Mining (AM) is the research area which aims at extracting argument components and predicting argumentative relations (i.e., support and attack) from text. In particular, numerous approaches have been proposed in the literature to predict the relations holding between arguments, and application-specific annotated resources were built for this purpose. Despite the fact that these resources were created to experiment on the same task, the definition of a single relation prediction method to be successfully applied to a significant portion of these datasets is an open research problem in AM. This means that none of the methods proposed in the literature can be easily ported from one resource to another. In this paper, we address this problem by proposing a set of dataset independent strong neural baselines which obtain homogeneous results on all the datasets proposed in the literature for the argumentative relation prediction task in AM. Thus, our baselines can be employed by the AM community to compare more effectively how well a method performs on the argumentative relation prediction task.

Original languageEnglish
Title of host publicationComputational Models of Argument - Proceedings of COMMA 2020
EditorsHenry Prakken, Stefano Bistarelli, Francesco Santini, Carlo Taticchi
PublisherIOS Press BV
Number of pages8
ISBN (Electronic)9781643681061
Publication statusPublished - 31 Aug 2020
Event8th International Conference on Computational Models of Argument, COMMA 2020 - Virtual, Online, Italy
Duration: 8 Sept 202011 Sept 2020

Publication series

NameFrontiers in Artificial Intelligence and Applications
ISSN (Print)0922-6389


Conference8th International Conference on Computational Models of Argument, COMMA 2020
CityVirtual, Online


  • Argument Mining
  • Machine Learning Methods
  • Relation Prediction


Dive into the research topics of 'Dataset independent baselines for relation prediction in argument mining'. Together they form a unique fingerprint.

Cite this