人工知能
Online ISSN : 2435-8614
Print ISSN : 2188-2266
人工知能学会誌(1986~2013, Print ISSN:0912-8085)
矛盾を含む知識の取り扱いについての一考察
斉藤 幹也浮田 善文松嶋 敏泰平澤 茂一
著者情報
解説誌・一般情報誌 フリー

1998 年 13 巻 2 号 p. 252-262

詳細
抄録

This study presents how to deal with knowledge when it includes contradiction. We propose the ways to reject contradiction and decide a true interpretation as correct as possible by clearing the cause of contradiction. In this paper, we assume two reasons why contradiction is occurred. For one reason, it occurs due to erroneous information from transmitters which sometimes provide wrong information. Another is circumstances are always changing, the change of true interpretation causes contradiction. We define these models, and decide true interpretation or construct consistent knowledge by calculating transmitters' error rates or interpretation changing rates. Further, we consider this field from our point of view. There are many studies in this field including belief revision, belief update, combining theory and multisource reasoning. These studies can be dividbd into two groups. One is semantics dependent problem, which is mainly based on minimal change principle. The other is syntax dependent problem, which is chiefly based on maximal consistent princible. Either of them does not consider what circumstance they should be applied to, and what they guarantee. In this paper, we can classify and evaluate past various works by our model, and clarify the meanings what they intend.

著者関連情報
© 1998 人工知能学会
前の記事 次の記事
feedback
Top