Valuing free-form text data from maintenance logs through transfer learning with CamemBERT
- 7 July 2020
- journal article
- research article
- Published by Taylor & Francis in Enterprise Information Systems
- Vol. 16 (6)
Abstract
Coupling a production scheduling process with maintenance logs can provide important advantages. For instance, this enables the adaptation of planning to the reality of the shop floor. Nevertheless, maintenance logs are often highly unstructured, as they mainly rely on free-form text comments from operators, and are imbalanced, as commonplace issues happen more often than critical problems. This hinders the application of machine learning methods to exploit this data. Thus, this study explores the use of a recent model named CamemBERT to tackle these difficulties through transfer learning. More specifically, the purpose is to predict the criticality and duration of a maintenance issue from the description provided. Findings suggest that fine-tuning CamemBERT outperforms other classical and feature-based approaches. Furthermore, the class imbalance problem is addressed from a data pre-processing and training perspective: firstly, k-means with silhouette diagrams allowed the creation of more homogenous classes, and secondly, the use of resampling enabled an improvement in the model’s performance.Keywords
Funding Information
- iFAKT France SAS and the ANRT (2018/1266)
This publication has 35 references indexed in Scilit:
- Research-paper recommender systems: a literature surveyInternational Journal on Digital Libraries, 2015
- Glove: Global Vectors for Word Representation2014
- A Comparison of MCC and CEN Error Measures in Multi-Class PredictionPLOS ONE, 2012
- Data Mining in Manufacturing: A ReviewJournal of Manufacturing Science and Engineering, 2005
- Performance measurement systems in SMEs: A review for a research agendaInternational Journal of Management Reviews, 2005
- Towards a Methodology for Developing Evidence‐Informed Management Knowledge by Means of Systematic ReviewBritish Journal of Management, 2003
- Sample Quantiles in Statistical PackagesThe American Statistician, 1996
- Silhouettes: A graphical aid to the interpretation and validation of cluster analysisJournal of Computational and Applied Mathematics, 1987
- A STATISTICAL INTERPRETATION OF TERM SPECIFICITY AND ITS APPLICATION IN RETRIEVALJournal of Documentation, 1972
- A Coefficient of Agreement for Nominal ScalesEducational and Psychological Measurement, 1960