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

Recent advance in Dense Retrieval (DR) techniques has significantly improvedthe effectiveness of first-stage retrieval. Trained with large-scale superviseddata, DR models can encode queries and documents into a low-dimensional densespace and conduct effective semantic matching. However, previous studies haveshown that the effectiveness of DR models would drop by a large margin when thetrained DR models are adopted in a target domain that is different from thedomain of the labeled data. One of the possible reasons is that the DR modelhas never seen the target corpus and thus might be incapable of mitigating thedifference between the training and target domains. In practice, unfortunately,training a DR model for each target domain to avoid domain shift is often adifficult task as it requires additional time, storage, and domain-specificdata labeling, which are not always available. To address this problem, in thispaper, we propose a novel DR framework named Disentangled Dense Retrieval (DDR)to support effective and flexible domain adaptation for DR models. DDR consistsof a Relevance Estimation Module (REM) for modeling domain-invariant matchingpatterns and several Domain Adaption Modules (DAMs) for modelingdomain-specific features of multiple target corpora. By making the REM and DAMsdisentangled, DDR enables a flexible training paradigm in which REM is trainedwith supervision once and DAMs are trained with unsupervised data.Comprehensive experiments in different domains and languages show that DDRsignificantly improves ranking performance compared to strong DR baselines andsubstantially outperforms traditional retrieval methods in most scenarios.

Disentangled Modeling of Domain and Relevance for Adaptable Dense Retrieval