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

Incorporating Item Response Theory (IRT) into NLP tasks can provide valuableinformation about model performance and behavior. Traditionally, IRT models arelearned using human response pattern (RP) data, presenting a significantbottleneck for large data sets like those required for training deep neuralnetworks (DNNs). In this work we propose learning IRT models using RPsgenerated from artificial crowds of DNN models. We demonstrate theeffectiveness of learning IRT models using DNN-generated data throughquantitative and qualitative analyses for two NLP tasks. Parameters learnedfrom human and machine RPs for natural language inference and sentimentanalysis exhibit medium to large positive correlations. We demonstrate ause-case for latent difficulty item parameters, namely training set filtering,and show that using difficulty to sample training data outperforms baselinemethods. Finally, we highlight cases where human expectation about itemdifficulty does not match difficulty as estimated from the machine RPs.

Learning Latent Parameters without Human Response Patterns: Item Response Theory with Artificial Crowds