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

Vector-based retrieval systems have become a common staple for academic andindustrial search applications because they provide a simple and scalable wayof extending the search to leverage contextual representations for documentsand queries. As these vector-based systems rely on contextual language models,their usage commonly requires GPUs, which can be expensive and difficult tomanage. Given recent advances in introducing sparsity into language models forimproved inference efficiency, in this paper, we study how sparse languagemodels can be used for dense retrieval to improve inference efficiency. Usingthe popular retrieval library Tevatron and the MSMARCO, NQ, and TriviaQAdatasets, we find that sparse language models can be used as directreplacements with little to no drop in accuracy and up to 4.3x improvedinference speeds

Dense Sparse Retrieval: Using Sparse Language Models for Inference Efficient Dense Retrieval