MaintNet: A Collaborative Open-Source Library for Predictive Maintenance Language Resources

Farhad Akhbardeh, Travis Desell, Marcos Zampieri


Abstract
Maintenance record logbooks are an emerging text type in NLP. An important part of them typically consist of free text with many domain specific technical terms, abbreviations, and non-standard spelling and grammar. This poses difficulties for NLP pipelines trained on standard corpora. Analyzing and annotating such documents is of particular importance in the development of predictive maintenance systems, which aim to improve operational efficiency, reduce costs, prevent accidents, and save lives. In order to facilitate and encourage research in this area, we have developed MaintNet, a collaborative open-source library of technical and domain-specific language resources. MaintNet provides novel logbook data from the aviation, automotive, and facility maintenance domains along with tools to aid in their (pre-)processing and clustering. Furthermore, it provides a way to encourage discussion on and sharing of new datasets and tools for logbook data analysis.
Anthology ID:
2020.coling-demos.2
Volume:
Proceedings of the 28th International Conference on Computational Linguistics: System Demonstrations
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Editors:
Michal Ptaszynski, Bartosz Ziolko
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics (ICCL)
Note:
Pages:
7–11
Language:
URL:
https://aclanthology.org/2020.coling-demos.2
DOI:
10.18653/v1/2020.coling-demos.2
Bibkey:
Cite (ACL):
Farhad Akhbardeh, Travis Desell, and Marcos Zampieri. 2020. MaintNet: A Collaborative Open-Source Library for Predictive Maintenance Language Resources. In Proceedings of the 28th International Conference on Computational Linguistics: System Demonstrations, pages 7–11, Barcelona, Spain (Online). International Committee on Computational Linguistics (ICCL).
Cite (Informal):
MaintNet: A Collaborative Open-Source Library for Predictive Maintenance Language Resources (Akhbardeh et al., COLING 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.coling-demos.2.pdf
Data
10,000 People - Human Pose Recognition Data