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

This study discusses the effect of semi-supervised learning in combinationwith pretrained language models for data-to-text generation. It is not knownwhether semi-supervised learning is still helpful when a large-scale languagemodel is also supplemented. This study aims to answer this question bycomparing a data-to-text system only supplemented with a language model, to twodata-to-text systems that are additionally enriched by a data augmentation or apseudo-labeling semi-supervised learning approach.  Results show that semi-supervised learning results in higher scores ondiversity metrics. In terms of output quality, extending the training set of adata-to-text system with a language model using the pseudo-labeling approachdid increase text quality scores, but the data augmentation approach yieldedsimilar scores to the system without training set extension. These resultsindicate that semi-supervised learning approaches can bolster output qualityand diversity, even when a language model is also present.

Neural Data-to-Text Generation Based on Small Datasets: Comparing the  Added Value of Two Semi-Supervised Learning Approaches on Top of a Large  Language Model