approved
TriplEx - Explaining with Triples

TRIPLEX is an explainability package for Transformer-based models fine-tuned on Natural Language Inference, Semantic Text Similarity, or Text Classification tasks. TRIPLEX explains Transformers-based models by extracting a set of facts from the input data, subsuming it by abstraction, and generating a set of weighted triples as explanation.

Tags
Data and Resources
To access the resources you must log in

This item has no data

Additional Info
Field Value
Accessibility Both
AccessibilityMode Download
AccessibilityMode API Access
AccessibilityMode OnLine Access
Availability On-Line
Basic rights Modification
CreationDate 2023-06-21 11:10
Creator Setzu, Mattia, [email protected], orcid.org/0000-0001-8351-9999
Documentation https://pypi.org/project/triplex/
Field/Scope of use Research only
Github https://github.com/msetzu/triplex/
Group Social Impact of AI and explainable ML
Owner Setzu, Mattia, [email protected], orcid.org/0000-0001-8351-9999
ProgrammingLanguage Python
Pypi https://pypi.org/project/triplex/
Sublicense rights No
Territory of use World Wide
Thematic Cluster Other
system:type Method
Management Info
Field Value
Author SETZU MATTIA
Maintainer SETZU MATTIA
Version 1
Last Updated 16 September 2023, 10:12 (CEST)
Created 24 June 2023, 01:14 (CEST)