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

Most research about natural language generation (NLG) relies on evaluationbenchmarks with limited references for a sample, which may result in poorcorrelations with human judgements. The underlying reason is that one semanticmeaning can actually be expressed in different forms, and the evaluation with asingle or few references may not accurately reflect the quality of the model'shypotheses. To address this issue, this paper presents a novel method, namedPara-Ref, to enhance existing evaluation benchmarks by enriching the number ofreferences. We leverage large language models (LLMs) to paraphrase a singlereference into multiple high-quality ones in diverse expressions. Experimentalresults on representative NLG tasks of machine translation, text summarization,and image caption demonstrate that our method can effectively improve thecorrelation with human evaluation for sixteen automatic evaluation metrics by+7.82% in ratio. We release the code and data athttps://github.com/RUCAIBox/Para-Ref.

Not All Metrics Are Guilty: Improving NLG Evaluation with LLM Paraphrasing