@article{sajjad-etal-2022-neuron,
title = "Neuron-level Interpretation of Deep {NLP} Models: A Survey",
author = "Sajjad, Hassan and
Durrani, Nadir and
Dalvi, Fahim",
editor = "Roark, Brian and
Nenkova, Ani",
journal = "Transactions of the Association for Computational Linguistics",
volume = "10",
year = "2022",
address = "Cambridge, MA",
publisher = "MIT Press",
url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2022.tacl-1.74/",
doi = "10.1162/tacl_a_00519",
pages = "1285--1303",
abstract = "The proliferation of Deep Neural Networks in various domains has seen an increased need for interpretability of these models. Preliminary work done along this line, and papers that surveyed such, are focused on high-level representation analysis. However, a recent branch of work has concentrated on interpretability at a more granular level of analyzing neurons within these models. In this paper, we survey the work done on neuron analysis including: i) methods to discover and understand neurons in a network; ii) evaluation methods; iii) major findings including cross architectural comparisons that neuron analysis has unraveled; iv) applications of neuron probing such as: controlling the model, domain adaptation, and so forth; and v) a discussion on open issues and future research directions."
}
Markdown (Informal)
[Neuron-level Interpretation of Deep NLP Models: A Survey](https://preview.aclanthology.org/jlcl-multiple-ingestion/2022.tacl-1.74/) (Sajjad et al., TACL 2022)
ACL