數位文件之資訊組織與主題分析自動化之技術與應用

資訊組織與主題分析是圖書館學的理論與實務中最主要的課題之一，其目的在探討如何分析並組織文件，以提供使用者便捷、有效的資訊服務。資訊組織與主題分析需要高度的知識加工處理，傳統上有賴於訓練有素的圖書館人員進行此項工作。由於資訊科技的持續進步，使得資訊組織與主題分析探討的很多課題有自動化處理的作法。本文便是在介紹筆者發展的一些自動化的方法，並探討其中的觀念、技術、應用、與其未來的影響。文中特別介紹自動化索引、索引典自動建構以及自動分類，並展示其應用範例，期使讀者能具備自動化作法的概念，以便有效運用現有的資訊科技，更有效率的進行資訊組織與主題分析的工作。

關鍵字

索引；檢索；索引典；分類；自動化

並列摘要

Information organization and subject analysis (IOSA) is the main concern in library science and library services. The goal of IOSA is about how to analyze and organize documents to provide effective and efficient information access. IOSA requires human knowledge involvement. Traditionally, only well-trained librarians are qualified for this task. Due to the advance of information technologies, many tasks about IOSA now have the automatic solutions. This article introduces these automatic approaches developed by the author. The concepts, techniques, applications and future impacts are explored. Specifically, this article describes the automatic ways of indexing, thesaurus construction, and text categorization. Application examples are demonstrated to allow readers better understand these approaches so that future IOSA could be achieved in a more efficient way, through the integration of human efforts and automatic methods.

並列關鍵字

Indexing ； Retrieval ； Thesaurus ； Classification ； Automatic

參考文獻

Chan, Lois Mai(1994).Cataloging and Classification: An Introduction.New York:McGraw-Hill.

Google Scholar

Gerard Salton(1989).Automatic Text Processing: The Transformation, Analysis, and Retrieval of Information by Computer.Addison-Wesley.

Google Scholar

Hsinchun Chen,Tak Yim,David Fye,Bruce Schatz(1995).Automatic Thesaurus Generation for an Electronic Community System.Journal of the American Society for Information Science.46(3),175-193.

Google Scholar

Hwee Tou Ng,Wei Boon Goh,Kok Leong Low(1997).Feature Selection, Perception Learning, and a Usability Case Study for Text Categorization.Proceedings of the 20th Annual International ACM-SIGIR Conference on Research and Development in Information Retrieval.(Proceedings of the 20th Annual International ACM-SIGIR Conference on Research and Development in Information Retrieval).