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

Recent research in decoding methods for Natural Language Generation (NLG)tasks has shown that MAP decoding is not optimal, because model probabilitiesdo not always align with human preferences. Stronger decoding methods,including Quality Estimation (QE) reranking and Minimum Bayes' Risk (MBR)decoding, have since been proposed to mitigate the model-perplexity-vs-qualitymismatch. While these decoding methods achieve state-of-the-art performance,they are prohibitively expensive to compute. In this work, we propose MBRfinetuning and QE finetuning which distill the quality gains from thesedecoding methods at training time, while using an efficient decoding algorithmat inference time. Using the canonical NLG task of Neural Machine Translation(NMT), we show that even with self-training, these finetuning methodssignificantly outperform the base model. Moreover, when using an external LLMas a teacher model, these finetuning methods outperform finetuning onhuman-generated references. These findings suggest new ways to leveragemonolingual data to achieve improvements in model quality that are on par with,or even exceed, improvements from human-curated data, while maintaining maximumefficiency during decoding.

MBR and QE Finetuning: Training-time Distillation of the Best and Most Expensive Decoding Methods