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

Web search provides a promising way for people to obtain information and hasbeen extensively studied. With the surgence of deep learning and large-scalepre-training techniques, various neural information retrieval models areproposed and they have demonstrated the power for improving search (especially,the ranking) quality. All these existing search methods follow a commonparadigm, i.e. index-retrieve-rerank, where they first build an index of alldocuments based on document terms (i.e., sparse inverted index) orrepresentation vectors (i.e., dense vector index), then retrieve and rerankretrieved documents based on similarity between the query and documents viaranking models. In this paper, we explore a new paradigm of informationretrieval with neither sparse nor dense index but only a model. Specifically,we propose a pre-training model-based IR system called DynamicRetriever. As forthis system, the training stage embeds the token-level and document-levelinformation (especially, document identifiers) of the corpus into the modelparameters, then the inference stage directly generates document identifiersfor a given query. Compared with existing search methods, the model-based IRsystem has two advantages: i) it parameterizes the traditional static indexwith a pre-training model, which converts the document semantic mapping into adynamic and updatable process; ii) with separate document identifiers, itcaptures both the term-level and document-level information for each document.Extensive experiments conducted on the public search benchmark MS MARCO verifythe effectiveness and potential of our proposed new paradigm for informationretrieval.

DynamicRetriever: A Pre-training Model-based IR System with Neither Sparse nor Dense Index