We have explored a novel method to find textual relations in electronic documents using genetic programming and semantic networks. This can be used for enhancing information retrieval and simplifying user interfaces. The automatic extraction of relations from text enables easier updating of electronic dictionaries and may reduce interface area both for search input and hit output on small screens such as cell phones and PDAs (Personal Digital Assistants).

Abstract not found

Abstract. In this paper we present NewsFlash, an adaptive search system that assists a searcher to efficiently search a library of stored TV news reports. The system automatically summarises the closed-caption subtitles embedded in the TV broadcasts and selects appropriate sentences to best describe report content in respect to the searcher’s query. During interaction the system selects useful terms from these summaries and uses these terms to update the display and potentially update a stored searcher profile. We evaluate the worth of our approach with real searchers and realistic information seeking scenarios. A novel means of testing the worth of a permanent profile of searchers ’ general interests is also proposed. Our results show that the adaptive techniques we propose can work well in multimedia search environments. 1

Abstract. In this paper, we describe the design and development of personal information assistant (PIA), a system aiming to meet individual needs of the searchers. The system’s goal is to provide more up-to-date and relevant information to users with respect to their needs and interests. The main component of the system is a profile learner for capturing temporal user needs, based on implicit feedback gathering techniques. It monitors the system usage, the documents viewed and other user actions in order to infer users ’ changing needs. 1

Abstract. Over recent years the amount of health related information available via the Internet has greatly increased, and is being provided by a vast array of information providers, from government-owned public bodies to charities and to individuals publishing based on their experiences. This paper addresses the two main challenges to using this information: information overload and information quality. It also proposes a unique solution to these problems that can be used across all medical conditions, by facilitating the personalisation of online information searches, and enabling patient access to a proposed common EPRS in Wales.

We introduce a news retrieval system on which we evaluated three alternative presentation strategies for online news retrieval. We used a user-oriented and task-oriented evaluation framework. The interfaces studied were Image, giving a grid of thumbnails for each story together with query-based summaries presented as tooltips, Summary, which displayed the summary information alongside each thumbnail, and Cluster, which grouped similar stories together and used the same display format as Image. The evaluation showed that the Summary Interface was preferred to the Image Interface, and that the Cluster Interface was helpful to users with a set task to complete. The implications of this study are also discussed in this paper. 1.

nordin Qfy.chalmers.se We have explored a novel method to find textual relations in electronic documents using genetic programming and semantic networks. This can be used for enhancing information retrieval and simplifying user interfaces. The automatic extraction of relations from text enables easier updating of electronic dictionaries and may reduce interface area both for search input and hit output on small screens such as cell phones and PDAs (Personal Digital Assistants).