CLMar 23, 2022

An Empirical Study of Memorization in NLP

arXiv:2203.12171v1649 citationsh-index: 45
Originality Incremental advance
AI Analysis

This work addresses the gap in empirical verification of memorization for NLP practitioners, though it is incremental as it builds on existing long-tail theory.

This paper tackles the problem of verifying memorization behavior in NLP models, finding that top-memorized training instances are atypical and their removal causes a more significant drop in test accuracy compared to random removal, with a method developed to attribute memorization to features negatively correlated with class labels.

A recent study by Feldman (2020) proposed a long-tail theory to explain the memorization behavior of deep learning models. However, memorization has not been empirically verified in the context of NLP, a gap addressed by this work. In this paper, we use three different NLP tasks to check if the long-tail theory holds. Our experiments demonstrate that top-ranked memorized training instances are likely atypical, and removing the top-memorized training instances leads to a more serious drop in test accuracy compared with removing training instances randomly. Furthermore, we develop an attribution method to better understand why a training instance is memorized. We empirically show that our memorization attribution method is faithful, and share our interesting finding that the top-memorized parts of a training instance tend to be features negatively correlated with the class label.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes