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

In recent years, neural models have often outperformed rule-based and classicMachine Learning approaches in NLG. These classic approaches are now oftendisregarded, for example when new neural models are evaluated. We argue thatthey should not be overlooked, since, for some tasks, well-designed non-neuralapproaches achieve better performance than neural ones. In this paper, the taskof generating referring expressions in linguistic context is used as anexample. We examined two very different English datasets (WEBNLG and WSJ), andevaluated each algorithm using both automatic and human evaluations. Overall,the results of these evaluations suggest that rule-based systems with simplerule sets achieve on-par or better performance on both datasets compared tostate-of-the-art neural REG systems. In the case of the more realistic dataset,WSJ, a machine learning-based system with well-designed linguistic featuresperformed best. We hope that our work can encourage researchers to considernon-neural models in future.

Non-neural Models Matter: A Re-evaluation of Neural Referring Expression Generation Systems