Summary of the project

There is a growing realisation that relevant information will be accessible increasingly across media, across contexts and across modalities. The retrieval of such information will depend on factors such as time, place, and history of interaction, task in hand, current user interests, etc. To achieve this, Information Retrieval (IR) models that go beyond the usual relevance-oriented approach will need to be developed so that they can be deployed effectively to enhance retrieval performance. This is important to meet the information access demands of today's users. As a matter of fact, the growing need to deliver information on request in a form that can be readily and easily digested continues to be a challenge.

In this project, we tackle the IR problem from a multidimensional perspective. Besides the dimension of relevance, we shall study how to endow the systems with advanced capabilities for novelty detection, redundancy filtering, subtopic detection, personalization and context-based retrieval. These dimensions will not only be considered for the basic retrieval task but also for other tasks such as automatic summarization, document clustering and categorization. This research tries therefore to open new ways to improve the quality of access to sources of information. Furthermore, the existence of different types of ’documents’ available online makes necessary to study the application of these dimensions for different media: web, text, XML and video.

We will investigate into efficient retrieval systems able to post-process the rankings of retrieved documents in order to filter out redundant information, detect automatically subtopics of interest and, eventually, direct the user to the specific parts/sections/passages/clusters of interest. In this way, the search processes would demand less effort from the users.

To achieve these challenging objectives, the project is supported by four research groups (Universidad de Granada (UGR), Universidad Autónoma de Madrid (UAM) and Universidad de A Coruña (UDC)). These teams have a broad experience into the IR field and, interestingly, they have been working on complementary IR models and scenarios. This background is a good base for initiating the coordinated plan designed to face the tasks proposed in this project.

Project RIM3 -  Webmaster -