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

While Out-of-distribution (OOD) detection has been well explored in computervision, there have been relatively few prior attempts in OOD detection for NLPclassification. In this paper we argue that these prior attempts do not fullyaddress the OOD problem and may suffer from data leakage and poor calibrationof the resulting models. We present PnPOOD, a data augmentation technique toperform OOD detection via out-of-domain sample generation using the recentlyproposed Plug and Play Language Model (Dathathri et al., 2020). Our methodgenerates high quality discriminative samples close to the class boundaries,resulting in accurate OOD detection at test time. We demonstrate that our modeloutperforms prior models on OOD sample detection, and exhibits lowercalibration error on the 20 newsgroup text and Stanford Sentiment Treebankdataset (Lang, 1995; Socheret al., 2013). We further highlight an importantdata leakage issue with datasets used in prior attempts at OOD detection, andshare results on a new dataset for OOD detection that does not suffer from thesame problem.

PnPOOD : Out-Of-Distribution Detection for Text Classification via Plug andPlay Data Augmentation