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

Deep pre-trained language models (e,g. BERT) are effective at large-scaletext retrieval task. Existing text retrieval systems with state-of-the-artperformance usually adopt a retrieve-then-reranking architecture due to thehigh computational cost of pre-trained language models and the large corpussize. Under such a multi-stage architecture, previous studies mainly focused onoptimizing single stage of the framework thus improving the overall retrievalperformance. However, how to directly couple multi-stage features foroptimization has not been well studied. In this paper, we design Hybrid ListAware Transformer Reranking (HLATR) as a subsequent reranking module toincorporate both retrieval and reranking stage features. HLATR is lightweightand can be easily parallelized with existing text retrieval systems so that thereranking process can be performed in a single yet efficient processing.Empirical experiments on two large-scale text retrieval datasets show thatHLATR can efficiently improve the ranking performance of existing multi-stagetext retrieval methods.

HLATR: Enhance Multi-stage Text Retrieval with Hybrid List Aware Transformer Reranking