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

In this paper, we present a generative retrieval method for sponsored searchengine, which uses neural machine translation (NMT) to generate keywordsdirectly from query. This method is completely end-to-end, which skips queryrewriting and relevance judging phases in traditional retrieval systems.Different from standard machine translation, the target space in the retrievalsetting is a constrained closed set, where only committed keywords should begenerated. We present a Trie-based pruning technique in beam search to addressthis problem. The biggest challenge in deploying this method into a realindustrial environment is the latency impact of running the decoder.Self-normalized training coupled with Trie-based dynamic pruning dramaticallyreduces the inference time, yielding a speedup of more than 20 times. We alsodevise an mixed online-offline serving architecture to reduce the latency andCPU consumption. To encourage the NMT to generate new keywords uncovered by theexisting system, training data is carefully selected. This model has beensuccessfully applied in Baidu's commercial search engine as a supplementaryretrieval branch, which has brought a remarkable revenue improvement of morethan 10 percents.

An end-to-end Generative Retrieval Method for Sponsored Search Engine --Decoding Efficiently into a Closed Target Domain