Brianne Brown

Learn More
In this paper we analyze two question answering tasks : the TREC-8 question answering task and a set of reading comprehension exams. First, we show that Q/A systems perform better when there are multiple answer opportunities per question. Next, we analyze common approaches to two subproblems: term overlap for answer sentence identification , and answer(More)
BACKGROUND Good interrater reliability is essential to minimize error variance and improve study power. Reasons why raters differ in scoring the same patient include information variance (different information obtained because of asking different questions), observation variance (the same information is obtained, but raters differ in what they notice and(More)
In this paper we analyze two question answering tasks : the TREC-8 question answering task and a set of reading comprehension exams. First, we show that Q/A systems perform better when there are multiple answer opportunities per question. Next, we analyze common approaches to two subproblems: term overlap for answer sentence identification , and answer(More)
A computerized data-base for the management of the out-patient clinic for diabetes and of the hospital diabetic patients has been developed by means of low cost commercial microcomputer. The program is able to supply lists of sets of patients chosen from user-defined characteristics. The system also allows the selected listin of recall letters for periodic(More)
  • 1