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

Data-driven methods have achieved notable performance on intent detection,which is a task to comprehend user queries. Nonetheless, they are controversialfor over-confident predictions. In some scenarios, users do not only care aboutthe accuracy but also the confidence of model. Unfortunately, mainstream neuralnetworks are poorly calibrated, with a large gap between accuracy andconfidence. To handle this problem defined as confidence calibration, wepropose a model using the hyperspherical space and rebalancedaccuracy-uncertainty loss. Specifically, we project the label vector ontohyperspherical space uniformly to generate a dense label representation matrix,which mitigates over-confident predictions due to overfitting sparce one-hotlabel matrix. Besides, we rebalance samples of different accuracy anduncertainty to better guide model training. Experiments on the open datasetsverify that our model outperforms the existing calibration methods and achievesa significant improvement on the calibration metric.

Confidence Calibration for Intent Detection via Hyperspherical Space and Rebalanced Accuracy-Uncertainty Loss