RÉSUMÉ. La tâche de notre recherche est de fournir le contexte de recherche à un moteur de recherche, i.e. étendre une requête. Nous proposons une méthode d’expansion automatique de requêtes basée sur la proximité des termes. Elle estime l’importance des termes candidats selon la proximité des termes de la requête dans les premiers documents retrouvés. L’évaluation sur les collections TREC indi...

In this paper, we present our participation in the Medical Records Track of TREC 2012. This is the second time we take part in this track. 50 new topics have been published in this year. The goal of this track is still to find relevant patients that have particular diseases and/or treatments. To achieve this goal, we try four methods which include popular techniques like query expansion, concep...

Bag of Visual Words (BoVW) is an effective framework for image retrieval. Query expansion (QE) further boosts retrieval performance by refining a query with relevant visual words found from the geometric consistency check between the query image and highly ranked retrieved images obtained from the first round of retrieval. Since QE checks the pairwise consistency between query and highly ranked...

............................................................................................................................ 2 Table of

In our TREC participation, we used an ensemble approach in query expansion. Query expansion, such as synonym expansion, had shown promising results in medical literature search. On the other hand, some of the 2011 papers reported worse results from expansion. Since there are multiple knowledge sources available and each resource has clear strengths and weaknesses, we tested the combination of t...

The research reported in this paper has both a scientific and a commercial aim. The scientific interest is to explore the use of contexts in order to improve the quality of information brokering. In this paper it is shown that contexts in information brokering can be exploited to enable four directions of query reformulation: up and down (standard query expansion) and sideway reformulations of ...

The CDS track investigates methods that could help physicians find relevant medical cases for patients they are dealing with. Concept based representation has been shown to be effective in biomedical domain. However, the basic concept based retrieval method may not perform well because of the additional restriction on each clinical cases. Therefore, in this paper, we explored two external resou...

ImageCLEF photo task of this year is a little different from those of previous years. The caption field in image annotations and the narrative field in the text queries are removed, and the visual queries (example images) are also removed from the image collection too. In the new definition, the information that can be employed for queries and images is less than before, so that it becomes hard...