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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Sparse document representations have been widely used to retrieve relevantdocuments via exact lexical matching. Owing to the pre-computed inverted index,it supports fast ad-hoc search but incurs the vocabulary mismatch problem.Although recent neural ranking models using pre-trained language models canaddress this problem, they usually require expensive query inference costs,implying the trade-off between effectiveness and efficiency. Tackling thetrade-off, we propose a novel uni-encoder ranking model, Sparse retriever usinga Dual document Encoder (SpaDE), learning document representation via the dualencoder. Each encoder plays a central role in (i) adjusting the importance ofterms to improve lexical matching and (ii) expanding additional terms tosupport semantic matching. Furthermore, our co-training strategy trains thedual encoder effectively and avoids unnecessary intervention in training eachother. Experimental results on several benchmarks show that SpaDE outperformsexisting uni-encoder ranking models.

SpaDE: Improving Sparse Representations using a Dual Document Encoder for First-stage Retrieval