Last changed 27 May 1999 ............... Length about 900 words (6000 bytes).
This is a WWW document maintained by Steve Draper, installed at http://www.psy.gla.ac.uk/~steve/gauguin/projects.html.

Web site logical path: [Gauguin main page] [Steve's Gauguin pages] [this page]

Proposed projects for Gauguin young researchers

This is a list of projects proposed by the Gauguin sites for their young researchers. Actual projects carried out may differ according to developments within the network, and to suit the researchers actually employed.

Collaborative filtering using logs (Glasgow)

An evaluation of the collaborative use of logs of information-seeking activity to filter and recommend multimedia information, both in competition and in combination with existing content-based retrieval systems.

Comparison between database and IR access methods (Glasgow)

To develop a sensible test to compare a database retrieval system with an IR system on the same data. A pilot project on this has already been run (on a tiny dataset). This topic forces us to address difficult questions about what a fair test could be, and so will advance the evaluation framework.

Automatic processes to support collective information retrieval (CLIPS IMAG)

When several users are simultaneously searching for information to achieve a collective task, they play different roles depending on their abilities, knowledge, previous experience and favourite search tools. To allow for cross-fertilisation during the search, communication tools are provided for participants to explicitly share their findings (documents, recommendations, etc.). With these tools, participants have to pursue two simultaneous goals: search on their own, and communicate their findings to the others. This can lead to a heavy cognitive overload.

As a complement to these tools, it is interesting to study which automatic or semi-automatic tools can be provided to lighten this cognitive load. The advances made in the field of query fusion and search results fusion can bring basic techniques to design a number of such tools, to combine both queries and results (documents and recommendations) originating from the various participants. Once tools are designed, an evaluation methodology has to be defined to measure how good they are, not only for their intrinsic performance, but also for their ability to lighten the cognitive load of users.

Usability of still image and video retrieval systems (CLIPS IMAG)

Several methods exist for the extraction of still image and video documents. For still images: colour, texture, shape extraction, and assignation to elements of the indexing vocabulary. For videos, analysis of the audio track and the image track are also a source of information for the content representation. The problem addressed here is the study of the adequacy of the fusion of all these heterogeneous sources of information according to the usability of the systems, according to query sessions and also to browsing. We will also focus on the need of additional sources of information (for instance textual descriptions, scripts for videos) to enhance the usability of such still image and video retrieval systems.

Smart Media (GMD)

Internet-based "ezines", electronic newspapers on demand, and other new information services revolutionised the mass media. The next step will integrate them into the users' personal information environment. GMD-IPSI participates in the development of Internet-based information-on-demand systems which organise new items according to user interests enriching them with more background information if requested. This entails the use of conceptual information retrieval and collaborative filtering techniques. The young researchers will develop adequate evaluation methods.

Scientific Digital Libraries (GMD)

The scientific community has moved on from on-line databases and pre-print servers to electronic journals and textbook collections. The next step will be information environments supporting teaching and research. Bringing heterogeneous knowledge sources together through semantic interpretation of user requests enhances the potential benefit of scientific information assembled from publishers, universities and labs. The young researcher will participate in a co-operation between GMD's central scientific library and IPSI aiming at new ways of providing and distributing technical reports.

Corporate Digital Libraries (GMD)

Imaging systems and electronic archives are being replaced by integrated document handling supporting virtual teams and companies. Our approach to integrated document handling is based on advanced database technologies and information presentation tools. Valuable assets can be communicated and reused in a flexible and secure way. The young researchers will actively participate in GMD's industrial cooperation projects in this area.

Collaboratories (GMD)

Integrated information environments - called "collaboratories" - allow the development of new ways of co-operation for cost-effective, high-quality, user-centred digital library resource creation, making feasible continuous resource advancement in user-developer partnerships. Here, GMD-IPSI takes part in a trans-Atlantic co-operation with partners active in DLI II. Again, young researchers will find challenging modelling and evaluation issues which will be explored in the Gauguin framework.

Analysing engineers during co-operative work (Risø)

A young researcher will be involved in the project on Ecological Information Systems that addresses the development of principles for design and evaluation of multimedia systems that support information seeking in complex co-operative work environments. This is a cornerstone activity of the Centre for Human Machine Interaction and it investigates the information seeking practices of engineers during co-operative work, the information they need, the heterogeneous sources they use and the strategies they apply, such as similarity searching.

Multimedia application of cognitive systems engineering framework (Risø)

Application of the cognitive systems engineering framework developed at Risø to the evaluation of multimedia information sources, e.g. documentation of work, drawings and images and people's expertise.

Novel interfaces for browsing (RGU)

Design and develop novel interfaces for browsing multimedia repositories, and undertake laboratory and workplace evaluation studies on the resultant interfaces. The studies may be initiated while on short-term visits to other partners.

Collective group information seeking (RGU)

Extend and develop existing information seeking tools (e.g. SketchTrieve) for collective use by (small) groups of users, and experiment with the resultant environment in an actual work setting, e.g. assisting librarians offering WWW search assistance to remote user clients.

Application of framework and techniques in industry (RGU)

Apply evaluation approaches developed elsewhere in the project, e.g. task-based evaluation in a real work environment, to systems developed by industrial affiliates. Such a project could be undertaken by a short-term visitor to our institution, and used to train our young researchers in the particular approach.

Workplace analysis of data structuring and retrieval tools (RGU)

Apply existing data structuring and retrieval tools (e.g. WebCluster toolset) to an actual user application, and undertake workplace studies of the resultant system.

Intranet information seeking evaluation (Ubilab)

Ubilab aim to develop and evaluate innovative tools based on results from our current Informia project in collaboration with real user communities within our organisation. In particular, tools that take into consideration user preferences, context, and task will be considered in combination with traditional techniques such as text/web indexing and retrieval systems and newer developments such as information mediation systems.

In this project the young-researcher will evaluate tools & techniques for information seeking in a large real-world intranet environment in the financial domain, involving analysis of domain, documents, tools, tasks, users, and information needs.

Mediated information seeking and customised information delivery (Ubilab)

Develop novel tools for mediated information seeking and customised information delivery, using profile-based and/or collaborative models of users' behaviour and interests, combined with traditional IR techniques.

Information retrieval models (Dortmund)

We want to consider user-oriented data (e. g. relevance feedback, profile, interactivity) in information retrieval models. Our probabilistic approaches allow already to incorporate various facets of the information retrieval process such as uncertain document representation and vague querying. Visiting researchers could add the user facets to our approaches.

Experimental environments (Dortmund)

We maintain full-text collections (TREC collections), image collections (e. g. Paris, FERMI), and a video collection. The representation of the semantics of the documents is kept in database management systems such as Postgres and Oracle. Various search engines (freewais-sf, wait, Hyspirit) can be used for carrying out system-oriented experiments. We are interested in extending our environment for large-scale experiments involving "real" users.

Evaluation methods and tools (Dortmund)

We are working on the interpretation of effectiveness measures. Foundation of the measures are the so-called distributions which represent rankings of documents. Visiting researchers could work on enhancing distributions for capturing the interactive behaviour of users. Also, we are interested in investigating evaluation methods for hypermedia retrieval where browsing and structural or referential links between document nodes play a crucial role.

Digital Library applications (Dortmund)

Within the Carmen project, the integrated IR/hypertext system under development will be applied for the German mathematics and physics networks (MathNet, http://www.math-net.de/ and PhysNet, http://www.physik.uni-oldenburg.de/EPS/PhysNet/, respectively) which contain all kinds of publications (e.g. technical reports, journals articles, proceedings, monographs) from these areas. Currently, we are gathering data about user interfaces and functionalities of various Digital Libraries. Visiting researchers could contribute in the design and evaluation of new interfaces for Digital Libraries.

Integration of novel information processing technologies (Sheffield)

Using simple automatic natural language extraction and summarisation techniques to complement statistical IR approaches to support interactive searching. This project will include laboratory-based retrieval tests incorporating user involvement.

A concept based approach to heterogeneous multimedia collection retrieval (Sheffield)

The project is to investigate the generation of metadata to aid the presentation of search results from diverse types of collections in a homogeneous fashion. The focus will be on the design of appropriate interface environments and interactive evaluative experiments for retrieval by end-users.

User interface design for innovative searching interaction (Sheffield)

Exploring user interfaces for query formulation and expansion in highly interactive experimental systems including the integration of querying and browsing support mechanisms. This would involve the development of prototypes and workplace evaluations which particularly take account of new forms of searching interactions.

Needs assessment and user profiles for a corporate information alerting service (Sheffield)

The emphasis is on the application of information needs assessments and analysis techniques for heterogeneous user groups in a large multinational pharmaceutical company and the design of an alerting system which generates both stereotypical and dynamic user profiles.

Applying task analysis to IR (Tampere)

One young researcher will be working on a long-term project on task-based information searching combining analysis of task processes to information retrieval and relevance assessments

Multilingual IR (Tampere)

Work is also required on application of IR and HCI evaluation techniques to multilingual IR. The researcher will gain experience in working with multilingual document collections, query - construction approaches and word normalisation for IR.

Image retrieval (Tampere)

Similarly, a project will be carried out so the young researchers will gain experience in the evaluation of content based image retrieval algorithms with a task based test collection of photos (or maybe videos).

Web site logical path: [Gauguin main page] [Steve's Gauguin pages] [this page]
[Top of this page]