English

Memorisation versus Generalisation in Pre-trained Language Models

Computation and Language 2022-03-16 v2 Machine Learning

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 low-resource 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.

Keywords

Cite

@article{arxiv.2105.00828,
  title  = {Memorisation versus Generalisation in Pre-trained Language Models},
  author = {Michael Tänzer and Sebastian Ruder and Marek Rei},
  journal= {arXiv preprint arXiv:2105.00828},
  year   = {2022}
}

Comments

15 pages, 25 figures. To be published in ACL2022

R2 v1 2026-06-24T01:43:49.314Z