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

Hybrid retrievers can take advantage of both sparse and dense retrievers.Previous hybrid retrievers leverage indexing-heavy dense retrievers. In thiswork, we study "Is it possible to reduce the indexing memory of hybridretrievers without sacrificing performance"? Driven by this question, weleverage an indexing-efficient dense retriever (i.e. DrBoost) and introduce aLITE retriever that further reduces the memory of DrBoost. LITE is jointlytrained on contrastive learning and knowledge distillation from DrBoost. Then,we integrate BM25, a sparse retriever, with either LITE or DrBoost to formlight hybrid retrievers. Our Hybrid-LITE retriever saves 13X memory whilemaintaining 98.0% performance of the hybrid retriever of BM25 and DPR. Inaddition, we study the generalization capacity of our light hybrid retrieverson out-of-domain dataset and a set of adversarial attacks datasets. Experimentsshowcase that light hybrid retrievers achieve better generalization performancethan individual sparse and dense retrievers. Nevertheless, our analysis showsthat there is a large room to improve the robustness of retrievers, suggestinga new research direction.

A Study on the Efficiency and Generalization of Light Hybrid Retrievers