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

It is challenging to train a good intent classifier for a task-orienteddialogue system with only a few annotations. Recent studies have shown thatfine-tuning pre-trained language models with a small amount of labeledutterances from public benchmarks in a supervised manner is extremely helpful.However, we find that supervised pre-training yields an anisotropic featurespace, which may suppress the expressive power of the semantic representations.Inspired by recent research in isotropization, we propose to improve supervisedpre-training by regularizing the feature space towards isotropy. We propose tworegularizers based on contrastive learning and correlation matrix respectively,and demonstrate their effectiveness through extensive experiments. Our mainfinding is that it is promising to regularize supervised pre-training withisotropization to further improve the performance of few-shot intent detection.The source code can be found at https://github.com/fanolabs/isoIntentBert-main.

Fine-tuning Pre-trained Language Models for Few-shot Intent Detection: Supervised Pre-training and Isotropization