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

Semantic hashing has become a powerful paradigm for fast similarity search inmany information retrieval systems. While fairly successful, previoustechniques generally require two-stage training, and the binary constraints arehandled ad-hoc. In this paper, we present an end-to-end Neural Architecture forSemantic Hashing (NASH), where the binary hashing codes are treated asBernoulli latent variables. A neural variational inference framework isproposed for training, where gradients are directly back-propagated through thediscrete latent variable to optimize the hash function. We also drawconnections between proposed method and rate-distortion theory, which providesa theoretical foundation for the effectiveness of the proposed framework.Experimental results on three public datasets demonstrate that our methodsignificantly outperforms several state-of-the-art models on both unsupervisedand supervised scenarios.

NASH: Toward End-to-End Neural Architecture for Generative Semantic Hashing