Probing Classifiers: Promises, Shortcomings, and Advances [article]

Yonatan Belinkov
2021 arXiv   pre-print
Probing classifiers have emerged as one of the prominent methodologies for interpreting and analyzing deep neural network models of natural language processing. The basic idea is simple -- a classifier is trained to predict some linguistic property from a model's representations -- and has been used to examine a wide variety of models and properties. However, recent studies have demonstrated various methodological limitations of this approach. This article critically reviews the probing
more » ... ers framework, highlighting their promises, shortcomings, and advances.
arXiv:2102.12452v4 fatcat:x7qfinepf5hydkbiba3qvbfeti