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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Multi-Intent Spoken Language Understanding (SLU), a novel and more complexscenario of SLU, is attracting increasing attention. Unlike traditional SLU,each intent in this scenario has its specific scope. Semantic informationoutside the scope even hinders the prediction, which tremendously increases thedifficulty of intent detection. More seriously, guiding slot filling with theseinaccurate intent labels suffers error propagation problems, resulting inunsatisfied overall performance. To solve these challenges, in this paper, wepropose a novel Scope-Sensitive Result Attention Network (SSRAN) based onTransformer, which contains a Scope Recognizer (SR) and a Result AttentionNetwork (RAN). Scope Recognizer assignments scope information to each token,reducing the distraction of out-of-scope tokens. Result Attention Networkeffectively utilizes the bidirectional interaction between results of slotfilling and intent detection, mitigating the error propagation problem.Experiments on two public datasets indicate that our model significantlyimproves SLU performance (5.4\% and 2.1\% on Overall accuracy) over thestate-of-the-art baseline.

A Scope Sensitive and Result Attentive Model for Multi-Intent Spoken Language Understanding