IMPROVING DOCUMENT ACCESSIBILITY THROUGH ONTOLOGY-BASED INFORMATION SHARING

Information plays a crucial role in the entire life cycle of a product, i.e. from conceptual design through use and maintenance to eventual disposal. Once key personnel move on from a company, vital know-how may only exist in archived product documents, leading to great interest in ways of extracting readily sharable information from them. Studies have shown that knowledge workers spend appreciable amounts of their productive time searching for information online, and that those searches often prove unsuccessful. In addition, most engineers have difficulty in formulating effective query terms and current keyword-based searches are inefficient for helping them to select better queries. It is commonly argued that this problem can be solved by giving explicit definitions to the information through an ontology. Ontology-based information sharing has the potential to reduce the effort expended by engineers on retrieval and reuse of existing information. This paper presents an approach that extracts domain concepts from the documents based on an ontology definition. In particular, the applications of information extraction and document enrichment through engineers’ comments are discussed. The EDIT engineering ontology is described, and its role in improving document enrichment is presented.

[1]  Fabio Rinaldi,et al.  Exploiting Technical Terminology for Knowledge Management , 2004, LSTKM@EKAW.

[2]  Israel Ben-Shaul,et al.  Automatically Organizing Bookmarks per Contents , 1996, Comput. Networks.

[3]  Andreas Abecker,et al.  Corporate Memories for Knowledge Management in Industrial Practice: Prospects and Challenges , 1998 .

[4]  Daniela Petrelli,et al.  Semantic Web-Based Document: Editing and Browsing in AktiveDoc , 2005, ESWC.

[5]  Marti A. Hearst Automatic Acquisition of Hyponyms from Large Text Corpora , 1992, COLING.

[6]  David E. Millard,et al.  Artequakt: Generating Tailored Biographies with Automatically Annotated Fragments from the Web , 2002, SAAKM@ECAI.

[7]  Ken M. Wallace,et al.  Understanding the knowledge needs of novice designers in the aerospace industry , 2004 .

[8]  Susan T. Dumais,et al.  Statistical semantics: analysis of the potential performance of keyword information systems , 1984 .

[9]  Steffen Staab,et al.  Bootstrapping an Ontology-Based Information Extraction System , 2003, Intelligent Exploration of the Web.

[10]  Paul H. Lewis,et al.  Question Answering Towards Automatic Augmentations of Ontology Instances , 2004, ESWS.

[11]  Saeema Ahmed,et al.  Encouraging reuse of design knowledge: a method to index knowledge , 2005 .

[12]  Ken M. Wallace,et al.  A Methodology for Creating Ontologies for Engineering Design , 2007, J. Comput. Inf. Sci. Eng..

[13]  Ralph Grishman,et al.  A Corpus-based Probabilistic Grammar with Only Two Non-terminals , 1995, IWPT.

[14]  Ralph Grishman,et al.  Information Extraction: Techniques and Challenges , 1997, SCIE.

[15]  Dietmar F. Rösner,et al.  From Natural Language Documents to Sharable Product Knowledge: A Knowledge Engineering Approach , 1998 .