Alexander Bondarenko

TL;DR: This paper is a condensed report on the third year of the TouchØ lab on argument retrieval held at CLEF 2022, where participants retrieved argumentative passages from a generic web crawl and images that show support or opposition to some stance were retrieved.

TL;DR: In this article, the authors investigate whether neural ranking models can be explained in terms of well-studied principles of document ranking by using established theories from axiomatic~IR, and propose a set of axioms to reproduce ranking decisions based on combinations of elementary constraints.

TL;DR: CAM (comparative argumentative machine), a novel open-domain IR system to argumentatively compare objects with respect to information extracted from the Common Crawl, is presented.

TL;DR: Touché is introduced, the first lab on Argument Retrieval featuring two subtasks: the retrieval of arguments from a focused debate collection to support argumentative conversations and the retrieval from a generic web crawl to answer comparative questions with argumentative results.