0
Research Papers

Developing Engineering Ontology for Information Retrieval

[+] Author and Article Information
Zhanjun Li

Purdue Research and Education Center for Information Systems in Engineering (PRECISE), Purdue University, West Lafayette, IN 47907-2024; School of Mechanical Engineering, Purdue University, West Lafayette, IN 47907-2024liz@purdue.edu

Victor Raskin

Purdue Research and Education Center for Information Systems in Engineering (PRECISE), Purdue University, West Lafayette, IN 47907-2024; Department of English and Linguistics, Purdue University, West Lafayette, IN 47907-2024vraskin@purdue.edu

Karthik Ramani1

Purdue Research and Education Center for Information Systems in Engineering (PRECISE), Purdue University, West Lafayette, IN 47907-2024; School of Mechanical Engineering, Purdue University, West Lafayette, IN 47907-2024; School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN 47907-2024ramani@purdue.edu

www.matrixone.com/.

http://protege.stanford.edu.

www.foolabs.com/xpdf/.

www.imaginestics.com.

http://www.ontologyportal.org/.

www.McMaster.com.

1

Corresponding author.

J. Comput. Inf. Sci. Eng 8(1), 011003 (Feb 14, 2008) (13 pages) doi:10.1115/1.2830851 History: Received December 05, 2006; Revised August 13, 2007; Published February 14, 2008

When engineering content is created and applied during the product life cycle, it is often stored and forgotten. Since search remains word based, engineers do not have the effective means to harness and reuse past designs and experiences. Current information retrieval approaches based on statistical methods and keyword matching do not satisfy users’ needs in the engineering domain. Therefore, we propose a new computational framework that includes an ontological basis and algorithms to retrieve unstructured engineering documents while handling complex queries. The results from the preliminary test demonstrate that our method outperforms the traditional keyword-based search with respect to the standard information retrieval measurement.

FIGURES IN THIS ARTICLE
<>
Copyright © 2008 by American Society of Mechanical Engineers
Your Session has timed out. Please sign back in to continue.

References

Figures

Grahic Jump Location
Figure 1

System architecture and functional modules

Grahic Jump Location
Figure 2

The schema of the knowledge source

Grahic Jump Location
Figure 3

A portion of the EO

Grahic Jump Location
Figure 4

Modules and process of concept tagging and indexing

Grahic Jump Location
Figure 5

Examples of the document tagging results: (a),(b) example of drawing notes; (c),(d) example of catalog descriptions. Note that letters in bold are the words from the original document or PartText. For the sake of clarity, (1) the title block in the drawing is not shown, (2) only parts of the tagged documents are illustrated, and (3) the PartText is ignored in (b).

Grahic Jump Location
Figure 6

Concept disambiguation process for the query “lock washer with zinc finish:” (a) Cscores of the matched concepts for the query keywords, (b) CDs and wCscores for the ambiguous concepts of keyword “lock,” (c) CDs and wCscores for the ambiguous concepts of keyword “washer,” and (d) CDs and wCscores for the ambiguous concepts of keyword “finish”

Grahic Jump Location
Figure 7

A portion of the EO in concept abstraction

Grahic Jump Location
Figure 8

User interface for design orienteering: (a) search interface and first level of EO concepts for navigation and (b) search interface and returned results categorized

Tables

Errata

Discussions

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In