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

Leveraging large amounts of unlabeled data using Transformer-likearchitectures, like BERT, has gained popularity in recent times owing to theireffectiveness in learning general representations that can then be furtherfine-tuned for downstream tasks to much success. However, training these modelscan be costly both from an economic and environmental standpoint. In this work,we investigate how to effectively use unlabeled data: by exploring thetask-specific semi-supervised approach, Cross-View Training (CVT) and comparingit with task-agnostic BERT in multiple settings that include domain and taskrelevant English data. CVT uses a much lighter model architecture and we showthat it achieves similar performance to BERT on a set of sequence taggingtasks, with lesser financial and environmental impact.

To BERT or Not to BERT: Comparing Task-specific and Task-agnostic Semi-Supervised Approaches for Sequence Tagging