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

The ability to detect intent in dialogue systems has become increasinglyimportant in modern technology. These systems often generate a large amount ofunlabeled data, and manually labeling this data requires substantial humaneffort. Semi-supervised methods attempt to remedy this cost by using a modeltrained on a few labeled examples and then by assigning pseudo-labels tofurther a subset of unlabeled examples that has a model prediction confidencehigher than a certain threshold. However, one particularly perilous consequenceof these methods is the risk of picking an imbalanced set of examples acrossclasses, which could lead to poor labels. In the present work, we describeTop-K K-Nearest Neighbor (TK-KNN), which uses a more robust pseudo-labelingapproach based on distance in the embedding space while maintaining a balancedset of pseudo-labeled examples across classes through a ranking-based approach.Experiments on several datasets show that TK-KNN outperforms existing models,particularly when labeled data is scarce on popular datasets such as CLINC150and Banking77. Code is available at https://github.com/ServiceNow/tk-knn

TK-KNN: A Balanced Distance-Based Pseudo Labeling Approach for Semi-Supervised Intent Classification