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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Large pretrained Transformer-based language models like BERT and GPT havechanged the landscape of Natural Language Processing (NLP). However, finetuning such models still requires a large number of training examples for eachtarget task, thus annotating multiple datasets and training these models onvarious downstream tasks becomes time consuming and expensive. In this work, wepropose a simple extension of the Prototypical Networks for few-shot textclassification. Our main idea is to replace the class prototypes by Gaussiansand introduce a regularization term that encourages the examples to beclustered near the appropriate class centroids. Experimental results show thatour method outperforms various strong baselines on 13 public and 4 internaldatasets. Furthermore, we use the class distributions as a tool for detectingpotential out-of-distribution (OOD) data points during deployment.

Meta-learning Pathologies from Radiology Reports using Variance Aware Prototypical Networks