The ReCAP Project: Similarity Methods for Finding Arguments and Argument Graphs

• Published in: Datenbank-Spektrum : Zeitschrift für Datenbanktechnologie : Organ der Fachgruppe Datenbanken der Gesellschaft für Informatik e.V 2020-07, Vol.20 (2), p.93-98
• Main Authors: Bergmann, Ralph, Biertz, Manuel, Dumani, Lorik, Lenz, Mirko, Ludwig, Anna-Katharina, Neumann, Patrick J., Ollinger, Stefan, Sahitaj, Premtim, Schenkel, Ralf, Witry, Alex
• Format: Article
• Language: English
• Subjects: Computer Science; Computer Systems Organization and Communication Networks; Data Mining and Knowledge Discovery; Data Structures and Information Theory; Database Management; Information Storage and Retrieval; IT in Business; Schwerpunktbeitrag
• ISSN: 1618-2162; 1610-1995
• DOI: 10.1007/s13222-020-00340-0

Argumentation Machines search for arguments in natural language from information sources on the Web and reason with them on the knowledge level to actively support the deliberation and synthesis of arguments for a particular user query. The recap project is part of the Priority Program ratio and aims at novel contributions to and confluence of methods from information retrieval, knowledge representation, as well as case-based reasoning for the development of future argumentation machines. In this paper we summarise recent research results from the project. In particular, a new German corpus of 100 semantically annotated argument graphs from the domain of education politics has been created and is made available to the argumentation research community. Further, we discuss a comprehensive investigation in finding arguments and argument graphs. We introduce a probabilistic ranking framework for argument retrieval, i.e. for finding good premises for a designated claim. For finding argument graphs, we developed methods for case-based argument retrieval considering the graph structure of an argument together with textual and ontology-based similarity measures applied to claims, premises, and argument schemes.