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 first-stage retrieval aims to retrieve a subset of candidate documentsfrom a huge collection both effectively and efficiently. Since various matchingpatterns can exist between queries and relevant documents, previous work triesto combine multiple retrieval models to find as many relevant results aspossible. The constructed ensembles, whether learned independently or jointly,do not care which component model is more suitable to an instance duringtraining. Thus, they cannot fully exploit the capabilities of different typesof retrieval models in identifying diverse relevance patterns. Motivated bythis observation, in this paper, we propose a Mixture-of-Experts (MoE) modelconsisting of representative matching experts and a novel competitive learningmechanism to let the experts develop and enhance their expertise duringtraining. Specifically, our MoE model shares the bottom layers to learn commonsemantic representations and uses differently structured upper layers torepresent various types of retrieval experts. Our competitive learningmechanism has two stages: (1) a standardized learning stage to train theexperts equally to develop their capabilities to conduct relevance matching;(2) a specialized learning stage where the experts compete with each other onevery training instance and get rewards and updates according to theirperformance to enhance their expertise on certain types of samples.Experimental results on three retrieval benchmark datasets show that our methodsignificantly outperforms the state-of-the-art baselines.

CAME: Competitively Learning a Mixture-of-Experts Model for First-stage Retrieval