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

Detecting Out-of-Domain (OOD) or unknown intents from user queries isessential in a task-oriented dialog system. Traditional softmax-basedconfidence scores are susceptible to the overconfidence issue. In this paper,we propose a simple but strong energy-based score function to detect OOD wherethe energy scores of OOD samples are higher than IND samples. Further, given asmall set of labeled OOD samples, we introduce an energy-based margin objectivefor supervised OOD detection to explicitly distinguish OOD samples from INDs.Comprehensive experiments and analysis prove our method helps disentangleconfidence score distributions of IND and OOD data.\footnote{Our code isavailable at \url{https://github.com/pris-nlp/EMNLP2022-energy_for_OOD/}.}

Disentangling Confidence Score Distribution for Out-of-Domain Intent Detection with Energy-Based Learning