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

Pre-trained Transformer-based models were reported to be robust in intentclassification. In this work, we first point out the importance of in-domainout-of-scope detection in few-shot intent recognition tasks and then illustratethe vulnerability of pre-trained Transformer-based models against samples thatare in-domain but out-of-scope (ID-OOS). We construct two new datasets, andempirically show that pre-trained models do not perform well on both ID-OOSexamples and general out-of-scope examples, especially on fine-grained few-shotintent detection tasks. To figure out how the models mistakenly classify ID-OOSintents as in-scope intents, we further conduct analysis on confidence scoresand the overlapping keywords, as well as point out several prospectivedirections for future work. Resources are available onhttps://github.com/jianguoz/Few-Shot-Intent-Detection.

Are Pretrained Transformers Robust in Intent Classification? A Missing Ingredient in Evaluation of Out-of-Scope Intent Detection