Search Results for author: Piotr Gawrysiak

Found 4 papers, 1 papers with code

Distance Metric Learning Loss Functions in Few-Shot Scenarios of Supervised Language Models Fine-Tuning

no code implementations28 Nov 2022 Witold Sosnowski, Karolina Seweryn, Anna Wróblewska, Piotr Gawrysiak

This paper presents an analysis regarding an influence of the Distance Metric Learning (DML) loss functions on the supervised fine-tuning of the language models for classification tasks.

Metric Learning

Revisiting Distance Metric Learning for Few-Shot Natural Language Classification

no code implementations28 Nov 2022 Witold Sosnowski, Anna Wróblewska, Karolina Seweryn, Piotr Gawrysiak

Our systematic experiments have shown that under few-shot learning settings, particularly proxy-based DML losses can positively affect the fine-tuning and inference of a supervised language model.

Few-Shot Learning Language Modelling +1

Applying SoftTriple Loss for Supervised Language Model Fine Tuning

no code implementations15 Dec 2021 Witold Sosnowski, Anna Wroblewska, Piotr Gawrysiak

We introduce a new loss function TripleEntropy, to improve classification performance for fine-tuning general knowledge pre-trained language models based on cross-entropy and SoftTriple loss.

General Knowledge Language Modelling

Cannot find the paper you are looking for? You can Submit a new open access paper.