Does My Representation Capture X? Probe-Ably
Machine Learning
2021-10-01 v2 Artificial Intelligence
Computation and Language
Abstract
Probing (or diagnostic classification) has become a popular strategy for investigating whether a given set of intermediate features is present in the representations of neural models. Probing studies may have misleading results, but various recent works have suggested more reliable methodologies that compensate for the possible pitfalls of probing. However, these best practices are numerous and fast-evolving. To simplify the process of running a set of probing experiments in line with suggested methodologies, we introduce Probe-Ably: an extendable probing framework which supports and automates the application of probing methods to the user's inputs.
Cite
@article{arxiv.2104.05807,
title = {Does My Representation Capture X? Probe-Ably},
author = {Deborah Ferreira and Julia Rozanova and Mokanarangan Thayaparan and Marco Valentino and André Freitas},
journal= {arXiv preprint arXiv:2104.05807},
year = {2021}
}
Comments
ACL 2021 (System Demonstrations)