Case-based reasoning to support annotating manuscripts in digital archives

Abstract

The process of manually annotating ancient manuscripts may rise a problem of verifying each user annotations. Thus, it is important to use a supporting system to correct certain annotations; this may be done on the basis of the experience of other users in similar cases. In this chapter, we present how we used case-based reasoning (CBR) in a digital archive to make a recommender system, which will accelerate the annotation process and correct user errors. In fact, our system tracks important user actions and saves those actions as traces. The CBR is applied to users' traces that are considered as users' experiences. Traces are structured in reusable sections called episodes (cases); each episode represents the work done on one document unit. Episode actions comprise both problems and solutions. The recommender system compares the current episode of the annotator trace with the traces database to find similar episodes, and recommends the most appropriate actions representing the solution to the user. At that point, the user takes the responsibility of accepting or refusing the recommendations. A prototype of this application has been developed to test the performance of using the CBR system in a digital archive. The experimental results confirmed the efficiency of using case-based reasoning in this domain. © 2014 Springer-Verlag Berlin Heidelberg.