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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Short text classification is a crucial and challenging aspect of NaturalLanguage Processing. For this reason, there are numerous highly specializedshort text classifiers. However, in recent short text research, State of theArt (SOTA) methods for traditional text classification, particularly the pureuse of Transformers, have been unexploited. In this work, we examine theperformance of a variety of short text classifiers as well as the topperforming traditional text classifier. We further investigate the effects ontwo new real-world short text datasets in an effort to address the issue ofbecoming overly dependent on benchmark datasets with a limited number ofcharacteristics. Our experiments unambiguously demonstrate that Transformersachieve SOTA accuracy on short text classification tasks, raising the questionof whether specialized short text techniques are necessary.

Transformers are Short Text Classifiers: A Study of Inductive Short Text Classifiers on Benchmarks and Real-world Datasets