The purpose of Information Retrieval (IR) systems is to provide users with relevant documents with respect to their query. Traditionally, what is considered as a relevant document is a document on the same topic as the query (i.e. topical relevance). However, systems are now integrating other relevance dimension, such as the novelty, the readability, etc.
In the medical domain, it is crucial to provide users with understandable and credible information, especially for layusers. To do so, systems must integrate into their relevance matching and ranking methods these aspects.
The purpose of this internship is to investigate how to efficiently conduct this integration and consider a personalization of medical search. Moreover, the question of the evaluation of such personalization will be considered, both from the system and from the user perspective.
This internship will be carried out in the context of the CLEF eHealth evaluation challenge (https://clefehealth.imag.fr/), an international benchmark activity led by members of the supervising team. This will give the student a unique opportunity to integrate the organization team, contribute to the publication of datasets and papers.
 Jimmy, J., Zuccon, G., Palotti, J., Goeuriot, L., & Kelly, L. (2018). Overview of the clef 2018 consumer health search task.
 Palotti, J., Goeuriot, L., Zuccon, G., & Hanbury, A. (2016, July). Ranking health web pages with relevance and understandability. In Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval (pp. 965-968).