English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

In low resource settings, deep neural models have often shown lowerperformance due to overfitting. The primary method to solve the overfittingproblem is to generalize model parameters. To this end, many researchers havedepended on large external resources with various manipulation techniques. Inthis study, we discuss how to exploit all available samples in low resourcesettings, without external datasets and model manipulation. This study focuseson natural language processing task. We propose a simple algorithm to find outgood initialization parameters that improve robustness to a small sample set.We apply early stopping techniques that enable the use of all samples fortraining. Finally, the proposed learning strategy is to train all samples withthe good initialization parameters and stop the model with the early stoppingtechniques. Extensive experiments are conducted on seven public sentenceclassification datasets, and the results demonstrate that the proposed learningstrategy achieves better performance than several state-of-the-art works acrossthe seven datasets.

Exploiting all samples in low-resource sentence classification: early stopping and initialization parameters