Project 14: Decision Theoretic models for IR

Host Organisation: Department of Informatics, Systems and CommunicationUniversity of Milano-Bicocca, Milan, Italy

Information Retrieval is in its very nature a decision process; in particular it can be seen as a Multi Criteria Decision Making activity, where the search system makes a decision based on a multiplicity of criteria/constraints, imposed both by the selected query terms, but also by the considered relevance dimensions.

The aim of this project is to define a general decision theoretic model for IR, based on a Multi Criteria Decision Making approach, with the following main objectives: (1) to analyse the properties of different aggregation operators within the Multi Criteria Decision Making model, also in relation to the contextual search paradigm (thus possibly defining different models); (2) to instantiate the defined models on the various applications (health, legal, patent), and (3) to evaluate the defined decision strategies.

The project encompasses issues related to the definition of decision theoretic (contextual) models for IR, and issues related to the definition of suitable evaluation strategies, for the various applications that will be considered.

This project has received funding from the European Union's Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No 860721