Overview of Touché 2023: Argument and Causal Retrieval - Extended Abstract

Alexander Bondarenko, Maik Fröbe, Johannes Kiesel, Ferdinand Schlatt, Valentin Barrière, Brian Ravenet, Léo Hemamou, Simon Luck, Jan Heinrich Reimer, Benno Stein, Martin Potthast, Matthias Hagen

Abstract: The goal of Touché is to foster and support the development of technologies for argument and causal retrieval and analysis. For the fourth time, we organize the Touché lab featuring four shared tasks: (a) argument retrieval for controversial topics, where participants retrieve web documents that contain high-quality argumentation and detect the argument stance, (b) causal retrieval, where participants retrieve documents that contain causal statements from a generic web crawl and detect the causal stance, (c) image retrieval for arguments, where participants retrieve images showing support or opposition to some stance from a focused web crawl, and (d) intra-multilingual multi-target stance classification, where participants detect the stance of comments on proposals from the multilingual participatory democracy platform CoFE. In this paper, we briefly summarize the results of Touché 2022 and describe the planned setup for the fourth lab edition at CLEF 2023.