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

Out-of-domain (OOD) input detection is vital in a task-oriented dialoguesystem since the acceptance of unsupported inputs could lead to an incorrectresponse of the system. This paper proposes OutFlip, a method to generateout-of-domain samples using only in-domain training dataset automatically. Awhite-box natural language attack method HotFlip is revised to generateout-of-domain samples instead of adversarial examples. Our evaluation resultsshowed that integrating OutFlip-generated out-of-domain samples into thetraining dataset could significantly improve an intent classification model'sout-of-domain detection performance.

OutFlip: Generating Out-of-Domain Samples for Unknown Intent Detection with Natural Language Attack