DOE OSTI · code-50372
Transformer eXplainability and eXploration
Abstract
The Transformer eXplainability and eXploration library is intended to aid in the explorability and explainability of transformer classification networks, or transformer language models with sequence classification heads. The basic function of this library is to take a trained transformer and test/train dataset and produce an ipywidget dashboard which can be displayed in a jupyter notebook or in jupyter lab.
Keep this discovery
Explore connections, maps & timelines
Martindale, Nathan [Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)] (0000000250365433), Stewart, ScottL. [Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)] (0000000343205818). 2021-01-29. Transformer eXplainability and eXploration. https://doi.org/10.11578/dc.20210129.1. https://engineeringpapers.com/record/osti%3Acode-50372/transformer-explainability-and-exploration
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Engineering Papers by Indiciae: BibTeX · RIS.