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

We study the coarse-grained selection module in retrieval-based chatbot.Coarse-grained selection is a basic module in a retrieval-based chatbot, whichconstructs a rough candidate set from the whole database to speed up theinteraction with customers. So far, there are two kinds of approaches forcoarse-grained selection module: (1) sparse representation; (2) denserepresentation. To the best of our knowledge, there is no systematic comparisonbetween these two approaches in retrieval-based chatbots, and which kind ofmethod is better in real scenarios is still an open question. In this paper, wefirst systematically compare these two methods from four aspects: (1)effectiveness; (2) index stoarge; (3) search time cost; (4) human evaluation.Extensive experiment results demonstrate that dense representation methodsignificantly outperforms the sparse representation, but costs more time andstorage occupation. In order to overcome these fatal weaknesses of denserepresentation method, we propose an ultra-fast, low-storage, and highlyeffective Deep Semantic Hashing Coarse-grained selection method, called DSHCmodel. Specifically, in our proposed DSHC model, a hashing optimizing modulethat consists of two autoencoder models is stacked on a trained denserepresentation model, and three loss functions are designed to optimize it. Thehash codes provided by hashing optimizing module effectively preserve the richsemantic and similarity information in dense vectors. Extensive experimentresults prove that, our proposed DSHC model can achieve much faster speed andlower storage than sparse representation, with limited performance losscompared with dense representation. Besides, our source codes have beenpublicly released for future research.

Ultra-Fast, Low-Storage, Highly Effective Coarse-grained Selection in Retrieval-based Chatbot by Using Deep Semantic Hashing