Towards a game-theoretic framework for text data retrieval

The task of text data retrieval has traditionally been defined as to rank a collection of text documents in response to a query. While this definition has enabled most research progress so far, it does not model accurately the actual retrieval task in a real search engine application, where users tend to be engaged in an interactive process with multipe queries, and optimizing the overall performance of a search engine system on an entire search session is far more important than its performance on an individual query. This paper presents a new game-theoretic formulation of the text data retrieval problem where the key idea is to model text retrieval as a process of a search engine and a user playing a cooperative game, with a shared goal of satisfying the user’s information need (or more generally helping the user complete a task) while minimizing the user’s effort and the operation cost of the retrieval system. Such a gametheoretic framework naturally optimizes the overall utility of an interactive retrieval system over a whole search session, thus breaking the limitation of the traditional formulation that optimizes ranking of documents for a single query and can optimize the collaboration of a search engine and its users, thus maximizing the “combined intelligence” of a system and users. Although the framework was motivated by text data retrieval, it is actually quite general and potentially applicable to all kinds of information