Mixed-Initiative Ontology Learning
نویسندگان
چکیده
This paper presents a mixed-initiative assistant that supports a subject matter expert to extend the ontology of a learning agent, in order to express the subtle distinctions he makes in an application domain. This assistant performs a comparative analysis of the correct examples and the exceptions accumulated by the problem solving rules and guides the expert in improving its knowledge base. This assistant is integrated into the Disciple-RKF system, and has been evaluated in two knowledge acquisition experiments performed at the US Army War College.
منابع مشابه
Mixed-Initiative Clustering
Mixed-initiative clustering is a task where a user and a machine work collaboratively to analyze a large set of documents. We hypothesize that a user and a machine can both learn better clustering models through enriched communication and interactive learning from each other. The first contribution of this thesis is providing a framework of mixedinitiative clustering. The framework consists of ...
متن کاملRule-Based Mixed-Initiative Scaffolding
The mechanism of Self-Regulated Learning (SRL) is a complex interactive process involving cognitive selfregulation. Self-regulation is enacted by learners when they form specific learning strategies that they actively or subconsciously adopt in order to enhance their learning experience. Our research concerns the development of a framework that allows for Mixed Initiative Interactions (MII) to ...
متن کاملApril 13 , 2010 Draft Mixed - Initiative Clustering
Mixed-initiative clustering is a task where a user and a machine work col-laboratively to analyze a large set of documents. We hypothesize that a user and a machine can both learn better clustering models through enriched communication and interactive learning from each other. The first contribution of this thesis is providing a framework of mixed-initiative clustering. The framework consists o...
متن کاملMixed - initiative Control for Teaching and Learning in Disciple
Disciple is an approach to agent development by subject matter experts where an expert teaches a Disciple agent his or her problem solving expertise in a way that resembles how a person teaches another person. This paper presents an overview of the teaching and learning process during which the expert helps Disciple to learn and Disciple helps the expert to teach it, emphasizing the mixed-initi...
متن کاملThe Label Complexity of Mixed-Initiative Classifier Training
Mixed-initiative classifier training, where the human teacher can choose which items to label or to label items chosen by the computer, has enjoyed empirical success but without a rigorous statistical learning theoretical justification. We analyze the label complexity of a simple mixed-initiative training mechanism using teaching dimension and active learning. We show that mixed-initiative trai...
متن کامل