Supporting Conversational Case-Based Reasoning in an Integrated Reasoning Framework
David W. Aha, Leonard A. Breslow · 2003
Conversational case-based reasoning (CCBR) has been successfully used to assist in case retrieval tasks. However, behavioral limitations of CCBR motivate the search for integrations with other reasoning approaches. This paper briefly describes our group's ongoing efforts towards enhancing the inferencing behaviors of a conversational case-based reasoning development tool named NaCoDAE. In particular, we focus on integrating NaCoDAE with machine learning, model-based reasoning, and generative planning modules. This paper defines CCBR, briefly summarizes the integrations, and explains how they enhance the overall system. Citation: NCARAI TR AIC-98-006 Conversational Case-Based Reasoning Our research focuses on enhancing the performance of conversational case-based reasoning (CCBR) systems (Aha & Breslow, 1997). CCBR is a form of case-based reasoning where users initiate problem solving conversations by entering an initial problem description in natural language text. This text is ass...