0
Research Papers

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, IL 61801
e-mail: skang47@illinois.edu

Lalit Patil

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

Arvind Rangarajan

General Electric Global Research,
Niskayuna, NY 12309
e-mail: arvind.rangarajan@ge.com

Abha Moitra

General Electric Global Research,
Niskayuna, NY 12309
e-mail: moitraa@ge.com

Dean Robinson

General Electric Global Research,
Niskayuna, NY 12309
e-mail: robinsondm@ge.com

Tao Jia

General Electric Healthcare,
Waukesha, WI 53188
e-mail: tjia@ge.com

Debasish Dutta

Professor
Mem. ASME
School of Engineering,
Rutgers University,
New Brunswick, NJ 08901
e-mail: dutta@oq.rutgers.edu

1Corresponding author.

Contributed by the Computers and Information Division of ASME for publication in the JOURNAL OF COMPUTING AND INFORMATION SCIENCE IN ENGINEERING. Manuscript received March 21, 2018; final manuscript received November 20, 2018; published online February 4, 2019. Assoc. Editor: Ying Liu.

J. Comput. Inf. Sci. Eng 19(2), 021003 (Feb 04, 2019) (9 pages) Paper No: JCISE-18-1070; doi: 10.1115/1.4042104 History: Received March 21, 2018; Revised November 20, 2018

Manufacturing companies maintain manufacturing knowledge primarily as unstructured text. To facilitate formal use of such knowledge, previous efforts have utilized natural language processing (NLP) to classify manufacturing documents or extract manufacturing concepts/relations. However, extracting more complex knowledge, such as manufacturing rules, has been evasive due to the lack of methods to resolve ambiguities. Specifically, standard NLP techniques do not address domain-specific ambiguities that are due to manufacturing-specific meanings implicit in the text. To address this important gap, we propose an ambiguity resolution method that utilizes domain ontology as the mechanism to incorporate the domain context. We demonstrate its feasibility by extending our previously implemented manufacturing rule extraction framework. The effectiveness of the method is demonstrated by resolving all the domain-specific ambiguities in the dataset and an improvement in correct detection of rules to 70% (increased by about 13%). We expect that this work will contribute to the adoption of semantics-based technology in manufacturing field, by enabling the extraction of precise formal knowledge from text.

Copyright © 2019 by ASME
Your Session has timed out. Please sign back in to continue.

References

Ur-Rahman, N. , and Harding, J. A. , 2012, “ Textual Data Mining for Industrial Knowledge Management and Text Classification: A Business Oriented Approach,” Expert Syst. Appl., 39(5), pp. 4729–4739. [CrossRef]
Boonyasopon, P. , Riel, A. , Uys, W. , Louw, L. , Tichkiewitch, S. , and du Preez, N. , 2011, “ Automatic Knowledge Extraction From Manufacturing Research Publications,” CIRP Ann.-Manuf. Technol., 60(1), pp. 477–480. [CrossRef]
Shotorbani, P. Y. , Ameri, F. , Kulvatunyou, B. , and Ivezic, N. , 2016, “ A Hybrid Method for Manufacturing Text Mining Based on Document Clustering and Topic Modeling Techniques,” IFIP International Conference on Advances in Production Management Systems, Iguassu Falls, Brazil, Sept. 3–7, pp. 777–786. https://ws680.nist.gov/publication/get_pdf.cfm?pub_id=920918
Li, Z. , and Ramani, K. , 2007, “ Ontology-Based Design Information Extraction and Retrieval,” Artif. Intell. Eng. Des. Anal. Manuf., 21(2), pp. 137–154. [CrossRef]
Cheong, H. , Li, W. , and Iorio, F. , 2016, “ Automated Extraction of System Structure Knowledge From Text,” ASME Paper No. DETC2016-59551.
Wang, G. , Tian, X. , Geng, J. , Evans, R. , and Che, S. , 2016, “ Extraction of Principle Knowledge From Process Patents for Manufacturing Process Innovation,” Procedia CIRP, 56, pp. 193–198. [CrossRef]
Li, Z. , Yang, M. C. , and Ramani, K. , 2009, “ A Methodology for Engineering Ontology Acquisition and Validation,” Artif. Intell. Eng. Des. Anal. Manuf., 23(1), pp. 37–51. [CrossRef]
Ameri, F. , Kulvatunyou, B. , Ivezic, N. , and Kaikhah, K. , 2014, “ Ontological Conceptualization Based on the SKOS,” ASME J. Comput. Inf. Sci. Eng., 14(3), p. 031006. [CrossRef]
Rangarajan, A. , Radhakrishnan, P. , Moitra, A. , Crapo, A. , and Robinson, D. , 2013, “ Manufacturability Analysis and Design Feedback System Developed Using Semantic Framework,” ASME Paper No. DETC2013-12028.
Kang, S. , Patil, L. , Rangarajan, A. , Moitra, A. , Jia, T. , Robinson, D. , and Dutta, D. , 2015, “ Extraction of Manufacturing Rules From Unstructured Text Using a Semantic Framework,” ASME Paper No. DETC2015-47556.
Franz, A. , 1996, Automatic Ambiguity Resolution in Natural Language Processing: An Empirical Approach, Vol. 1171, Springer, Berlin.
Poesio, M. , Stuckardt, R. , and Versley, Y. , 2016, Anaphora Resolution: Algorithms, Resources, and Applications, Springer, Berlin.
Lappin, S. , and Leass, H. J. , 1994, “ An Algorithm for Pronominal Anaphora Resolution,” Comput. Linguist., 20(4), pp. 535–561.
Mitkov, R. , 1994, “ An Integrated Model for Anaphora Resolution,” 15th Conference on Computational Linguistics, Kyoto, Japan, Aug. 5–9, pp. 1170–1176.
Mitkov, R. , 1998, “ Robust Pronoun Resolution With Limited Knowledge,” 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics, Montreal, QC, Canada, Aug. 10–14, pp. 869–875.
Dagan, I. , and Itai, A. , 1990, “ Automatic Processing of Large Corpora for the Resolution of Anaphora References,” 13th Conference on Computational Linguistics, Helsinki, Finland, Aug. 20–25, pp. 330–332.
Iida, R. , Inui, K. , and Matsumoto, Y. , 2005, “ Anaphora Resolution by Antecedent Identification Followed by Anaphoricity Determination,” ACM Trans. Asian Lang. Inf. Process., 4(4), pp. 417–434. [CrossRef]
Lee, H. , Chang, A. , Peirsman, Y. , Chambers, N. , Surdeanu, M. , and Jurafsky, D. , 2013, “ Deterministic Coreference Resolution Based on Entity-Centric, Precision-Ranked Rules,” Comput. Linguist., 39(4), pp. 885–916. [CrossRef]
Ponzetto, S. P. , and Strube, M. , 2006, “ Exploiting Semantic Role Labeling, Wordnet and Wikipedia for Coreference Resolution,” Main Conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics, New York, June 4–9, pp. 192–199.
Miller, G. A. , 1995, “ WordNet: A Lexical Database for English,” Commun. ACM, 38(11), pp. 39–41. [CrossRef]
Bryl, V. , Giuliano, C. , Serafini, L. , and Tymoshenko, K. , 2010, “ Supporting Natural Language Processing With Background Knowledge: Coreference Resolution Case,” International Semantic Web Conference (ISWC), Shanghai, China, Nov. 7–11, pp. 80–95.
Auer, S. , Bizer, C. , Kobilarov, G. , Lehmann, J. , Cyganiak, R. , and Ives, Z. , 2007, “ DBpedia: A Nucleus for a Web of Open Data,” The Semantic Web, Springer, Berlin, pp. 722–735.
Suchanek, F. M. , Kasneci, G. , and Weikum, G. , 2007, “ YAGO: A Core of Semantic Knowledge,” 16th International Conference on World Wide Web, Banff, AB, Canada, May 8–12, pp. 697–706.
Uryupina, O. , Poesio, M. , Giuliano, C. , and Tymoshenko, K. , 2011, “ Disambiguation and Filtering Methods in Using Web Knowledge for Coreference Resolution,” FLAIRS Conference, Palm Beach, FL, May 18--20, pp. 317–322.
Resnik, P. , 1999, “ Semantic Similarity in a Taxonomy: An Information-Based Measure and Its Application to Problems of Ambiguity in Natural Language,” J. Artif. Intell. Res., 11, pp. 95–130. [CrossRef]
Nakov, P. , and Hearst, M. , 2005, “ Using the Web as an Implicit Training Set: Application to Structural Ambiguity Resolution,” Conference on Human Language Technology and Empirical Methods in Natural Language Processing, Vancouver, BC, Canada, Oct. 6–8, pp. 835–842.
Ogren, P. V. , 2010, “ Improving Syntactic Coordination Resolution Using Language Modeling,” Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop, Los Angeles, CA, June 1–6, pp. 1–6.
Hanamoto, A. , Matsuzaki, T. , and Tsujii, J. , 2012, “ Coordination Structure Analysis Using Dual Decomposition,” 13th Conference of the European Chapter of the Association for Computational Linguistics, Avignon, France, Apr. 23–27, pp. 430–438.
Nilsson, J. , Nivre, J. , and Hall, J. , 2006, “ Graph Transformations in Data-Driven Dependency Parsing,” 21st International Conference on Computational Linguistics and the 44th Annual Meeting of the Association for Computational Linguistics, Sydney, Australia, July 20, pp. 257–264.
Hogan, D. , 2007, “ Coordinate Noun Phrase Disambiguation in a Generative Parsing Model,” 45th Annual Meeting of the Association of Computational Linguistics, Prague, Czech Republic, June 23–30, pp. 680–687.
Choi, D. J. , “ The Natural Language Processing for JVM Languages (NLP4J),” JVM Languages, Santa Clara, CA, accessed Oct. 12, 2018, https://emorynlp.github.io/nlp4j/
Bralla, J. , 1998, Design for Manufacturability Handbook, McGraw-Hill Professional, New York.
Ameri, F. , and Dutta, D. , 2006, “ An Upper Ontology for Manufacturing Service Description,” ASME Paper No. DETC2006-99600.
Crapo, A. , and Moitra, A. , 2013, “ Toward a Unified English-Like Representation of Semantic Models, Data, and Graph Patterns for Subject Matter Experts,” Int. J. Semantic Comput., 7(3), pp. 215–236. [CrossRef]
Kottmann, J. , Ingersoll, G. , Drost, I. , Kosin, J. , Baldridge, J. , Morton, T. , Silva, W. , Agerri, R. , Autayeu, A. , Galitsky, B. , Giaconia, M. , Teofili, T. , Khuc, V. , Beylerian, A. , Bouazizi, M. , Mattmann, C. , Mensikova, A. , Marthi, S. , Russ, D. , Thygesen, P. , Sekiguchi, K. , Kinoshita, P. B. , and Zemerick, J. , 2018, “ Apache OpenNLP,” Apache Software Foundation, Forest Hill, MD, accessed Oct. 12, 2018, https://opennlp.apache.org/
Seaborne, A. , Soroka, A. , Kinoshita, B. , Dollin, C. , Tomlinson, C. , Warren, C. , Steer, D. , Reynolds, D. , Dickinson, I. , Buehmann, L. , Suominen, O. , Castagna, P. , Vesse, R. , Allen, S. , and Jiang, Y. , 2018, “ Apache Jena,” Apache Software Foundation, Forest Hill, MD, accessed Oct.12, 2018, https://jena.apache.org/

Figures

Grahic Jump Location
Fig. 1

The motivating example involving the ambiguous phrase slot widths and radii: (a) the slot could modify either only widths (bottom-left) or both widths and radii (bottom-right), (b) the formal rule extracted without proper ambiguity resolution showing the unresolved component (null and those) due to the domain-specific ambiguity

Grahic Jump Location
Fig. 2

The overview of the ambiguity resolution method. The block arrows indicate the sequence of execution, and the solid arrows indicate the use of tool or knowledge base.

Grahic Jump Location
Fig. 3

The extraction of manufacturing concepts and relations from the motivating example. Natural language terms/grammatical relations are identified from the text, and then transformed to manufacturing concepts/relations(or attributes) defined in the manufacturing domain ontology.

Grahic Jump Location
Fig. 4

The coordination ambiguity in the motivating example. The coordination ambiguity occurs since the term slot modifies the coordinated terms widths and radii. It is ambiguous if the term slot modifies only the adjacent term widths or both widths and radii.

Grahic Jump Location
Fig. 5

Another example of coordination ambiguity. The coordination ambiguity occurs since the coordinated terms inside and outside modify the term corners. It is ambiguous if the phrase meant separate inside corners and outside corners, or the corners are inside and outside at the same time.

Grahic Jump Location
Fig. 6

The anaphoric ambiguity in the motivating example. The anaphoric ambiguity occurs since the referent of the pronoun those is not provided by standard NLP techniques.

Grahic Jump Location
Fig. 7

For the coordination ambiguity in the motivating example, the additional relation compound is created (shown as the dotted arrow) to identify all the possible interpretations

Grahic Jump Location
Fig. 8

For the coordination ambiguity involving the phrase inside and outside corner, additional term corners and relation nmod are created (shown as the dotted rectangular node and arrow) to identify all the possible interpretations

Grahic Jump Location
Fig. 9

For the anaphoric ambiguity in the motivating example, the additional relations coref are created (shown as the dotted arrows) to identify all the possible interpretations

Grahic Jump Location
Fig. 10

The resolution of the coordination ambiguity in the motivating example, occurred by one modifying term and coordinated nouns. Since the manufacturing concept slot has the attribute hasRadius in the manufacturing domain ontology, the additional compound relation is kept (shown as the dotted arrow). As a result, the term slot is regarded to modify both width and radii.

Grahic Jump Location
Fig. 11

The resolution of coordination ambiguity. Since there is the manufacturing concept InsideCorner corresponding to inside corner, the additional concept corner is kept (shown as the dotted rectangular node). As a result, the phrase inside and outside corners is regarded to mean separate inside corners and outside corners.

Grahic Jump Location
Fig. 12

The resolution of the anaphoric ambiguity in the motivating example. Since the manufacturing concept slot has the attribute hasWidths and hasRadius, but does not have hasSlot, the relation coref to the term slot is pruned (shown as the faded arrow), while the other coref are kept (shown as the solid dotted arrows). As a result, the pronoun those is regarded to refer only widths and radii.

Grahic Jump Location
Fig. 13

The formal manufacturing rule extracted from the motivating example, after ambiguity resolution. The unresolved components null and those in the motivating example (Fig. 1(b)) are successfully addressed.

Grahic Jump Location
Fig. 14

A part of MSDL (first three subfigures) and the manufacturing ontology (the last subfigure). We extend MSDL concepts/relations (e.g., surface) to define more specific concepts (e.g., EntranceSurface and ExitSurface).

Grahic Jump Location
Fig. 15

The comparison of the extracted formal rules, before and after ambiguity resolution for the sentence, inside and outside corners of a part should not be sharp. The separate InsideCorner and OutsideCorner are correctly captured after ambiguity resolution.

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