Indiscriminabilité dans les espaces de représentation des termes et des documents

Abstract

Examining the properties of representation spaces for documents or words in Information Retrieval (IR) – typically R n with n large– brings precious insights to help the retrieval process. Recently, several authors have studied the real dimensionality of the datasets, called intrinsic dimensionality, in specific parts of these spaces (Houle et al., 2012). They have shown that this dimensionality is chiefly tied with the notion of indiscriminability among neighbors of a query point in the vector space. In this paper, we propose to revisit this notion in the specific case of IR and to study its use in IR tasks. More precisely, we show how to estimate α from IR similarities and to use it in representtion spaces used for documents and words (Mikolov et al., 2013 ; Claveau et al., 2014). Indeed, we prove that α may be used to characterize difficult queries; moreover we show that this indiscriminability notion, applied to words, can help to choose terms to use for query expansion.