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

The information retrieval community has made significant progress inimproving the efficiency of Dual Encoder (DE) dense passage retrieval systems,making them suitable for latency-sensitive settings. However, many proposedprocedures are often too complex or resource-intensive, which makes itdifficult for practitioners to adopt them or identify sources of empiricalgains. Therefore, in this work, we propose a trivially simple recipe to serveas a baseline method for boosting the efficiency of DE retrievers leveraging anasymmetric architecture. Our results demonstrate that even a 2-layer,BERT-based query encoder can still retain 92.5% of the full DE performance onthe BEIR benchmark via unsupervised distillation and proper studentinitialization. We hope that our findings will encourage the community tore-evaluate the trade-offs between method complexity and performanceimprovements.

Query Encoder Distillation via Embedding Alignment is a Strong Baseline Method to Boost Dense Retriever Online Efficiency