0
research-article

Ontology-based Ambiguity Resolution of Manufacturing Text for Formal Rule Extraction

[+] Author and Article Information
Sungku Kang

Department of Mechanical Science and Engineering, University of Illinois at Urbana-Champaign, Urbana, Illinois 61801
skang47@illinois.edu

Lalit Patil

Department of Mechanical Science and Engineering, University of Illinois at Urbana-Champaign, Urbana, Illinois 61801
lpatil@ford.com

Arvind Rangarajan

General Electric Global Research, Niskayuna, New York 12309
arvind.rangarajan@ge.com

Abha Moitra

General Electric Global Research, Niskayuna, New York 12309
moitraa@ge.com

Dean Robinson

General Electric Global Research, Niskayuna, New York 12309
robinsondm@ge.com

Tao Jia

General Electric Healthcare, Waukesha, Wisconsin 53188
tjia@ge.com

Debasish Dutta

Professor, Member of ASME, Rutgers University, New Brunswick, New Jersey 08901
dutta@oq.rutgers.edu

1Corresponding author.

ASME doi:10.1115/1.4042104 History: Received March 21, 2018; Revised November 20, 2018

Abstract

Manufacturing knowledge is maintained primarily in unstructured text in industry. To facilitate the reuse of the knowledge in unstructured text, previous efforts have utilized Natural Language Processing (NLP) to classify manufacturing documents or to extract manufacturing concepts and their hierarchies (e.g. ontology) from text. On the other hand, extracting more complex knowledge, such as formal manufacturing rules, has not been successful due to the lack of proper ambiguity resolution. Specifically, domain-specific ambiguities, that are due to manufacturing-specific meanings implicit in the English text, are not resolved by standard NLP techniques as they do not consider manufacturing domain context. To address the important gap, we developed the ambiguity resolution method that utilizes domain ontology as the mechanism to incorporate manufacturing domain context. We proved the feasibility of the method by extending the previously implemented formal manufacturing rule extraction framework. Specifically, the effectiveness of the method is demonstrated by resolving all the domain-specific ambiguities in the dataset, and an increasing the correct rules to 70% (increased by approx. 13%). We expect that the ambiguity resolution method will contribute to the adoption of semantics-based technology in manufacturing field, by enabling the extraction of precise formal knowledge from textual knowledge.

Copyright (c) 2018 by ASME
Your Session has timed out. Please sign back in to continue.

References

Figures

Tables

Errata

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