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

Traditional training paradigms for extractive and abstractive summarizationsystems always only use token-level or sentence-level training objectives.However, the output summary is always evaluated from summary-level which leadsto the inconsistency in training and evaluation. In this paper, we propose aContrastive Learning based re-ranking framework for one-stage summarizationcalled COLO. By modeling a contrastive objective, we show that thesummarization model is able to directly generate summaries according to thesummary-level score without additional modules and parameters. Extensiveexperiments demonstrate that COLO boosts the extractive and abstractive resultsof one-stage systems on CNN/DailyMail benchmark to 44.58 and 46.33 ROUGE-1score while preserving the parameter efficiency and inference efficiency.Compared with state-of-the-art multi-stage systems, we save more than 100 GPUtraining hours and obtaining 3~8 speed-up ratio during inference whilemaintaining comparable results.

COLO: A Contrastive Learning based Re-ranking Framework for One-Stage Summarization