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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Search systems often employ a re-ranking pipeline, wherein documents (orpassages) from an initial pool of candidates are assigned new ranking scores.The process enables the use of highly-effective but expensive scoring functionsthat are not suitable for use directly in structures like inverted indices orapproximate nearest neighbour indices. However, re-ranking pipelines areinherently limited by the recall of the initial candidate pool; documents thatare not identified as candidates for re-ranking by the initial retrievalfunction cannot be identified. We propose a novel approach for overcoming therecall limitation based on the well-established clustering hypothesis.Throughout the re-ranking process, our approach adds documents to the pool thatare most similar to the highest-scoring documents up to that point. Thisfeedback process adapts the pool of candidates to those that may also yieldhigh ranking scores, even if they were not present in the initial pool. It canalso increase the score of documents that appear deeper in the pool that wouldhave otherwise been skipped due to a limited re-ranking budget. We find thatour Graph-based Adaptive Re-ranking (GAR) approach significantly improves theperformance of re-ranking pipelines in terms of precision- and recall-orientedmeasures, is complementary to a variety of existing techniques (e.g., denseretrieval), is robust to its hyperparameters, and contributes minimally tocomputational and storage costs. For instance, on the MS MARCO passage rankingdataset, GAR can improve the nDCG of a BM25 candidate pool by up to 8% whenapplying a monoT5 ranker.

Adaptive Re-Ranking with a Corpus Graph