資訊管理學報
戚玉樑;
頁: 193-215
日期: 2006/04
摘要: 以本體(Ontology)為基礎的知識庫建置中，開發者須將領域內的認知轉換為系統可處理的本體概念架構，其過程通常概分為知識擷取及知識表達等兩階段，知識擷取的方式若過於武斷則易形成不具共識的概念，而轉換為系統用的概念架構時，也須面臨階層確認及表達方式的轉置。本研究以目前常用的正規概念分析法（應用於知識擷取）及描述邏輯（應用於知識表達）為基礎，探討兩者的使用、問題及不協調處，並分別提出修正作業，另外也提出如何發展未知概念的探索方法。本研究提供一個應用修正方法所建立的本體範例，其結果顯示：修正後的方法是以先收集抽象及客觀的形成因素為主，具體及主觀的概念命名為最終步驟，因此本體概念的形成較符合認知的發展程序。
關鍵字: 本體;知識擷取;知識表達;正規概念分析法;描述邏輯;
Abstract: This study proposes an ontology building process for extracting conceptual structures and representing conceptual contents. Though humans have been developing ontologies for many years, building a well defined ontology of an interested domain is extremely ad-hoc. The objectives of this study include: (1) Revising FCA operations to elicit knowledge based on collecting cognition, deriving explicit and implicit concept, and finally naming concept tags; (2). Constructing conceptual hierarchies according to least common subsumer approach and representing conceptual contents by description language. The empirical feedback indicates that proposed approach provides suitable elicitation processes of knowledge acquisition and representation during ontology building. Additionally, this approach is especially useful for ontology developers who lack reference models of a working domain.
Keywords: Ontology;Knowledge Acquisition;Knowledge Representation;Formal Concept Analysis;and Description Logic;
瀏覽次數: 8849 下載次數: 90
引用 導入Endnote
頁: 193-215
日期: 2006/04
摘要: 以本體(Ontology)為基礎的知識庫建置中，開發者須將領域內的認知轉換為系統可處理的本體概念架構，其過程通常概分為知識擷取及知識表達等兩階段，知識擷取的方式若過於武斷則易形成不具共識的概念，而轉換為系統用的概念架構時，也須面臨階層確認及表達方式的轉置。本研究以目前常用的正規概念分析法（應用於知識擷取）及描述邏輯（應用於知識表達）為基礎，探討兩者的使用、問題及不協調處，並分別提出修正作業，另外也提出如何發展未知概念的探索方法。本研究提供一個應用修正方法所建立的本體範例，其結果顯示：修正後的方法是以先收集抽象及客觀的形成因素為主，具體及主觀的概念命名為最終步驟，因此本體概念的形成較符合認知的發展程序。
關鍵字: 本體;知識擷取;知識表達;正規概念分析法;描述邏輯;
Applying Knowledge Acquisition and Knowledge Representation Synergy to Construct Ontology Conceptual Structures
Abstract: This study proposes an ontology building process for extracting conceptual structures and representing conceptual contents. Though humans have been developing ontologies for many years, building a well defined ontology of an interested domain is extremely ad-hoc. The objectives of this study include: (1) Revising FCA operations to elicit knowledge based on collecting cognition, deriving explicit and implicit concept, and finally naming concept tags; (2). Constructing conceptual hierarchies according to least common subsumer approach and representing conceptual contents by description language. The empirical feedback indicates that proposed approach provides suitable elicitation processes of knowledge acquisition and representation during ontology building. Additionally, this approach is especially useful for ontology developers who lack reference models of a working domain.
Keywords: Ontology;Knowledge Acquisition;Knowledge Representation;Formal Concept Analysis;and Description Logic;
瀏覽次數: 8849 下載次數: 90
引用 導入Endnote