Generalising Ripple-Down Rules
نویسندگان
چکیده
Ripple-Down Rules (RDR) has the goal of simple, incremental development of a knowledge-based system (KBS) while the KBS is already in use, so that over time an expert can evolve a sophisticated KBS as a minor extension of their normal duties. RDR has had considerable success in developing classification KBS. It has been extended to configuration, heuristic search and other tasks. This paper proposes a generalisation of RDR that may enable experts to evolve KBS for a range of tasks.
منابع مشابه
Generalising Symbolic Knowledge in Online Classification and Prediction
Increasingly, researchers and developers of knowledge based systems (KBS) have been incorporating the notion of context. For instance, Repertory Grids, Formal Concept Analysis (FCA) and Ripple-Down Rules (RDR) all integrate either implicit or explicit contextual information. However, these methodologies treat context as a static entity, neglecting many connectionists’ work in learning hidden an...
متن کاملMultiple Classification Ripple Down Rules : Evaluation and Possibilities
Ripple Down Rules (RDR) is a knowledge acquisition method which constrains the interactions between the expert and a shell to acquire only correct knowledge. Although RDR works well, it is only suitable for the problem of providing a single classification for a set of data. Multiple Classification Ripple Down Rules (MCRDR) is an extension of RDR which allows multiple independent classifications...
متن کاملRipple Down Rules, a practical method of learning from code rewrites
Software developers sometimes rewrite large sections of program code. Reducing the number of rewrites would save valuable development time. Ripple Down Rules (RDR) has a proven knowledge acquisition track record. RDR looks to offer a simple to maintain method capturing knowledge gained through experience. RDR allows recommendations identified when a failure occurs, to be captured and reused. Th...
متن کاملExtending Ripple-Down Rules
Ripple-Down Rules (RDR) has had considerable success in providing simple incremental knowledge acquisition in classification domains. It has been extended to multiple classification, configuration, search and more recently to resource allocation tasks. Based on the experience of applying RDR to a resource allocation task, this paper proposes a generalisation of RDR to enable it to apply to a wi...
متن کاملLearning Ripple down Rules for Efficient Lemmatization
The paper presents a system, LemmaGen, for learning Ripple Down Rules specialized for automatic generation of lemmatizers. The system was applied to 14 different lexicons and produced efficient lemmatizers for the corresponding languages. Its evaluation on the 14 lexicons shows that LemmaGen considerably outperforms the lemmatizers generated by the original RDR learning algorithm, both in terms...
متن کامل