Session: DFMLC-05-01: Special Session: Design Tool Showcase & Design for Manufacturing and the Life Cycle in response to COVID-19

Paper Number: 71710

Start Time: August 19, 11:10 AM

71710 - Nestor: A Technical Language Processing (TLP) Tagging Tool 

For domain experts to benefit from advances in Natural Language Processing (NLP), a new approach toward annotating and structuring technical text is required, driven by community development of new tools.
We propose a user-centered approach to data labeling that aids in achieving what we term Technical Language Processing (TLP): a holistic, domain-driven approach to using NLP in a technical engineering setting. 

Nestor is a software tool that annotates natural language CSV (comma-separated variable) files, using a process called tagging. Maintenance work orders (MWOs) provide the health history of an asset and they are rich with information about the maintenance of a specific machine or asset. The objective of Nestor is to help analysts make their natural language data, which is often unstructured, filled with technical content, jargon, mispellings, and abbreviations, computable to improve analysis.  Nestor provides a human-in-the-loop solution to annotate the MWO natural language data for use in maintenance operations analysis. Engagement from Human Computer Interaction (HCI) and Human Factors community should be central to achieving what we see as fundamentally a form of Artificial Intelligence Augmentation (AIA), so that experts not only benefit from burgeoning algorithmic systems, but are able to trust the systems and the decisions they support.

Presenting Author: Michael Brundage National Institute of Standards and Technology (NIST)

Authors:

Thurston Sexton National Institute of Standards and Technology
Michael P. Brundage National Institute of Standards and Technology