Capability Language Processing (CLP): Classification and Ranking of Manufacturing Suppliers Based on Unstructured Capability Data
Date
2022-05
Authors
Zandbiglari, Kimia
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
In manufacturing industry, data is available in both structured and unstructured
forms. Although the unstructured data represented in natural language text contains
valuable information and knowledge, its effective processing for the sake of information
retrieval and knowledge extraction is a challenge. Manufacturing Capability data is an
example of unstructured data widely used for describing the technological capabilities of
manufacturing companies. The objective of this research is to use a set of text analytics
techniques to enable automated classification and ranking of manufacturing companies
based on their capability narratives available on their websites. For this purpose, a
supervised classification method is used in conjunction with semantic similarity
measurement method. A formal thesaurus that uses Simple Knowledge Organization
System (SKOS) format provides structural and lexical semantics to support classification
and ranking. To conduct semantic similarity measurement, edge-based method is
combined with Normalized Google Distance (NGD) technique to create a weighted edgebased method for measuring the similarities of manufacturers’ capabilities with the
queried capabilities provided by customers. The proposed framework is validated
experimentally using a hypothetical search scenario. The results indicate that the
generated ranked list is highly correlated with human judgment, especially if the query
model and supplier capability model belong to the same class. However, the correlation
decreases when multiple overlapping classes of suppliers are mixed. The findings of this
research can be used to improve the precision and reliability of Capability Language Processing (CLP) tools and methods and improve the intelligence of supplier discovery
and capability mapping platforms.
Description
Keywords
Capability Language Processing (CLP), Capability modeling, Text mining, Document classification, Formal thesaurus, Semantic similarity
Citation
Zandbiglari, K. (2022). <i>Capability Language Processing (CLP): Classification and ranking of manufacturing suppliers based on unstructured capability data</i> (Unpublished thesis). Texas State University, San Marcos, Texas.