Towards Multilingual User Models for Personalized Multilingual Information Retrieval

Abstract

The majority of studies in Personalized Information Retrieval (PIR) literature have focused on monolingual IR, and only relatively little work has been done concerning multilingual IR. In this paper we propose a novel method to represent user models in a multilingual fashion. We argue that such representation would be more suitable for Personalized Multilingual Information Retrieval (PMIR). Furthermore, we outline two algorithms for query adaptation based on user information from the multilingual user model.