paper-with-me

Papers

Memorisation versus Generalisation in Pre-trained Language Models

2021-04-16 · ACL 2022 5 · Michael Tänzer, Sebastian Ruder, Marek Rei

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.

📄 PDF Abstract BibTeX arXiv:2105.00828

Code (1)

Michael-Tanzer/BERT-mem-lowres 공식 구현 pytorch

Tasks

Few-Shot LearningLow Resource Named Entity Recognitionnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
WordPiece 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Attention 설명 없음
Residual Connection 설명 없음
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…

Similar Papers 제목 키워드 기반

Generalisation First, Memorisation Second? Memorisation Localisation for Natural Language Classification Tasks

2024-08-09 · Verna Dankers, Ivan Titov

Memorisation is a natural part of learning from real-world data: neural models pick up on atypical input-output combinations and store those training examples in their parameter space. That this happens is well-known, bu…

image-classificationImage Classification

Memorisation Cartography: Mapping out the Memorisation-Generalisation Continuum in Neural Machine Translation

2023-11-09 · Verna Dankers, Ivan Titov, Dieuwke Hupkes

When training a neural network, it will quickly memorise some source-target mappings from your dataset but never learn some others. Yet, memorisation is not easily expressed as a binary feature that is good or bad: indiv…

counterfactualMachine TranslationNMTPosition

What do larger image classifiers memorise?

2023-10-09 · Michal Lukasik, Vaishnavh Nagarajan, Ankit Singh Rawat, Aditya Krishna Menon 외

The success of modern neural networks has prompted study of the connection between memorisation and generalisation: overparameterised models generalise well, despite being able to perfectly fit (memorise) completely rand…

image-classificationImage ClassificationKnowledge DistillationMemorization+1

SoK: Memorisation in machine learning

2023-11-06 · Dmitrii Usynin, Moritz Knolle, Georgios Kaissis

Quantifying the impact of individual data samples on machine learning models is an open research problem. This is particularly relevant when complex and high-dimensional relationships have to be learned from a limited sa…

Do Smaller Language Models Answer Contextualised Questions Through Memorisation Or Generalisation?

2023-11-21 · Tim Hartill, Joshua Bensemann, Michael Witbrock, Patricia J. Riddle

A distinction is often drawn between a model's ability to predict a label for an evaluation sample that is directly memorised from highly similar training samples versus an ability to predict the label via some method of…

Question AnsweringSemantic SimilaritySemantic Textual Similarity