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

We address the problem of calibrating prediction confidence for outputentities of interest in natural language processing (NLP) applications. It isimportant that NLP applications such as named entity recognition and questionanswering produce calibrated confidence scores for their predictions,especially if the system is to be deployed in a safety-critical domain such ashealthcare. However, the output space of such structured prediction models isoften too large to adapt binary or multi-class calibration methods directly. Inthis study, we propose a general calibration scheme for output entities ofinterest in neural-network based structured prediction models. Our proposedmethod can be used with any binary class calibration scheme and a neuralnetwork model. Additionally, we show that our calibration method can also beused as an uncertainty-aware, entity-specific decoding step to improve theperformance of the underlying model at no additional training cost or datarequirements. We show that our method outperforms current calibrationtechniques for named-entity-recognition, part-of-speech and question answering.We also improve our model's performance from our decoding step across severaltasks and benchmark datasets. Our method improves the calibration and modelperformance on out-of-domain test scenarios as well.

Calibrating Structured Output Predictors for Natural Language Processing