Probing Classifiers: Promises, Shortcomings, and Advances | Computational Linguistics | MIT Press

Yonatan Belinkov; Probing Classifiers: Promises, Shortcomings, and Advances. Computational Linguistics 2022; 48 (1): 207–219. doi: https://doi.org/10.1162/coli_a_00422 Download citation file: 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 squib critically reviews the probing classifiers framework, highlighting their promises, shortcomings, and advances. The opaqueness of deep neural network models of natural language processing (NLP) has spurred a line of research into interpreting and analyzing them. Analysis methods may aim to answer questions about a model’s structure or its decisions. For

Yonatan Belinkov; Probing Classifiers: Promises, Shortcomings, and Advances. Computational Linguistics 2022; 48 (1): 207–219. doi: https://doi.org/10.1162/coli_a_00422 Download citation file: 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 methodologi