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

In intent detection tasks, leveraging meaningful semantic information fromintent labels can be particularly beneficial for few-shot scenarios. However,existing few-shot intent detection methods either ignore the intent labels,(e.g. treating intents as indices) or do not fully utilize this information(e.g. only using part of the intent labels). In this work, we present anend-to-end One-to-All system that enables the comparison of an input utterancewith all label candidates. The system can then fully utilize label semantics inthis way. Experiments on three few-shot intent detection tasks demonstrate thatOne-to-All is especially effective when the training resource is extremelyscarce, achieving state-of-the-art performance in 1-, 3- and 5-shot settings.Moreover, we present a novel pretraining strategy for our model that utilizesindirect supervision from paraphrasing, enabling zero-shot cross-domaingeneralization on intent detection tasks. Our code is athttps://github.com/jiangshdd/AllLablesTogether.

All Labels Together: Low-shot Intent Detection with an Efficient Label Semantic Encoding Paradigm