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

Discovering out-of-domain (OOD) intent is important for developing new skillsin task-oriented dialogue systems. The key challenges lie in how to transferprior in-domain (IND) knowledge to OOD clustering, as well as jointly learn OODrepresentations and cluster assignments. Previous methods suffer from in-domainoverfitting problem, and there is a natural gap between representation learningand clustering objectives. In this paper, we propose a unified K-nearestneighbor contrastive learning framework to discover OOD intents. Specifically,for IND pre-training stage, we propose a KCL objective to learn inter-classdiscriminative features, while maintaining intra-class diversity, whichalleviates the in-domain overfitting problem. For OOD clustering stage, wepropose a KCC method to form compact clusters by mining true hard negativesamples, which bridges the gap between clustering and representation learning.Extensive experiments on three benchmark datasets show that our method achievessubstantial improvements over the state-of-the-art methods.

Watch the Neighbors: A Unified K-Nearest Neighbor Contrastive Learning Framework for OOD Intent Discovery