Servicenavigation

Project Details

Back

Projekt Print View

SPP 1999:  Robust Argumentation Machines (RATIO)

Subject Area Computer Science, Systems and Electrical Engineering
Humanities
Social and Behavioural Sciences
Term since 2017
Project identifier Deutsche Forschungsgemeinschaft (DFG) - Project number 313723125
 
In situations involving complex decision making, individuals and organisations face a multitude of alternatives. Given the amount of available information, automatic support is indispensable for finding relevant facts and arguments, analysing them in a given context, and summarizing them. However, there is a lack of suitable technologies to do so. Systems like IBM Watson operate on facts as isolated units of information, and although they can extract those from texts efficiently, they are not able to contextualise or validate arguments. Analyses that detect correlations only (even when exploiting big data) obviously fall short in this respect, as they neither provide explanations nor contribute to rationalization. In the context of man-machine interaction, generating explanations is crucial, e.g. in order to offer an explanation of the faulty behaviour of a machine, or to support users and operators during fault repair.The Priority Programme strives for a paradigm shift in information technology such that single facts as the elementary units of information will be replaced by argumentative structures. This requires robust and scalable methods that are capable of extracting arguments and their contexts from documents, as well as new semantic models and ontologies for the deep representation of arguments and argument chains. New search technology is required in order to index arguments, find relevant pro and con arguments for a given hypothesis or proposition, and render the results interactively available for the user. In addition, new techniques for automated reasoning need to be developed in order to assess the plausibility of arguments and their consequences. Following the definition of Eemeren et al. [1996, 2014], we understand argumentation as a dialectical process in which a set of propositions with particular implications is disputed, with the goal to make one's own position comprehensible, conclusive and acceptable for a rational third party. Arguments are usually subjective and imperfect in the sense that they are based on implicit or wrong assumptions, stay vague and ambiguous, or their formulation remains incomplete. This makes the analysis of natural language arguments a very challenging endeavour, requiring focused research efforts and innovations that combine methods from the following core disciplines: information retrieval (IR), computational linguistics (CL), knowledge representation and inference (RI), Semantic Web (SW), and man-machine interaction (MMI). The Priority Programme aims at the development of methods that are able to capture arguments in a robust and scalable manner, in particular representing, contextualising, and aggregating arguments and making them available to a user. The development should be guided by four fundamental scenarios.
DFG Programme Priority Programmes
International Connection Poland, United Kingdom

Projects

 
 

Additional Information

© 2024 DFG Disclaimer / Copyright / Privacy Policy

Textvergrößerung und Kontrastanpassung