This paper presents the user-centered interface of a summarization system for physicians in Bone Marrow Transplan-tation (BMT). It serves both retrieval and summarization, eliciting the query and presenting multi-document summaries in a situation-specific organization.
SimSum (Simulation of Summarizing) simulates 20 real-world working steps of expert summarizers. It presents an empirically founded cognitive model of summarizing and demonstrates that human summarization strategies can be simulated. The cognitive model operationalizes the discourse processing model developed by Kintsch and van Dijk (1983). Knowledge… (More)
1 report on an empirical approach to expert summarizing , emphasizing the qualitative modeling methods that shaped the system. In the framework of model-based knowledge engineering, the empirical grounded theory of summarizing is subsequently transferred to a small simulation system called SimSum (Simulation of Summarizing). SimSum shows that an empirical… (More)
The advantage of cognitively motivated automatic summarizing is that human users can better understand what happens. This improves acceptability. The basic empirical finding in human summarizers is that they combine a choice of intellectual strategies. We report here on SummIt-BMT (Summarize It in Bone Marrow Transplantation), a prototype system that… (More)
We describe an ontology for WWW summarization in Bone Marrow Transplantation that is currently under construction. It is text-based and qualifies as a grounded ontology. In addition, it is user-centered. For stating medical knowledge, we use first-order logic extended with contexts. The ontology is prepared to serve query scenario formulation, text passage… (More)
SimSum (Slmulatxon of Summarizing) simulates 20 real-world worlang steps of expert summarizers It presents an empmcally founded cogm-Uve model of summarizing that oper-aUonahzes the discourse processing model developed by van Dijk and Kmtsch (1983) The observed strate-.gles of expert summarizers have g~ven nse to cooperating object-on-ented agents… (More)