About this Abstract |
Meeting |
MS&T23: Materials Science & Technology
|
Symposium
|
Materials Informatics for Images and Multi-dimensional Datasets
|
Presentation Title |
Topic Modelling Framework for Rapid Digestion of Additive Manufacturing Literature |
Author(s) |
Benjamin M. Glaser |
On-Site Speaker (Planned) |
Benjamin M. Glaser |
Abstract Scope |
Structural topic modelling typically requires a hands-on iterative process of industry experts reading, labelling, and sorting texts executed by a panels of domain experts. We have developed a pipeline using Latent Dirichlet Allocation (LDA) to accelerate topic identification and Natural Language Processing (NLP) to generate representative topic labels to reduce cognitive overhead. The capabilities of this program will be demonstrated on a dataset of US patent office publications and journal articles relevant to additive
manufacturing to compare trends in recent years. The focus of this component of the exploration will be on areas of focus for additive manufacturing machines, as in the patent literature, and developments in alloy design via journal publications. |