Memorisation versus generalisation in pre-trained language models
File(s)
Preprint version
OA Location
Author(s)
Tänzer, Michael
Ruder, Sebastian
Rei, Marek
Type
preprint
Abstract
State-of-the-art pre-trained language models have been shown to memorise facts and perform well with limited amounts of training data. To gain a better understanding of how these models learn, we study their generalisation and memorisation capabilities in noisy and low-resource scenarios. We find that the training of these models is almost unaffected by label noise and that it is possible to reach near-optimal results even on extremely noisy datasets. However, our experiments also show that they mainly learn from high-frequency patterns and largely fail when tested on lowresource tasks such as few-shot learning and rare entity recognition. To mitigate such limitations, we propose an extension based on prototypical networks that improves performance in low-resource named entity recognition tasks.
Date Issued
2022-03-15
Citation
arXiv, 2022
Journal / Book Title
arXiv
Copyright Statement
Copyright © 2022 The Authors.
Description
Preprint version
Identifier
http://arxiv.org/abs/2105.00828v2
Subjects
cs.CL
cs.CL
cs.LG