Engineering Papers⌕ Search

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

BibTeXRIS

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.