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 introduce distributed NLI, a new NLU task with a goal to predict thedistribution of human judgements for natural language inference. We show thatby applying additional distribution estimation methods, namely, Monte Carlo(MC) Dropout, Deep Ensemble, Re-Calibration, and Distribution Distillation,models can capture human judgement distribution more effectively than thesoftmax baseline. We show that MC Dropout is able to achieve decent performancewithout any distribution annotations while Re-Calibration can give furtherimprovements with extra distribution annotations, suggesting the value ofmultiple annotations for one example in modeling the distribution of humanjudgements. Despite these improvements, the best results are still far belowthe estimated human upper-bound, indicating that predicting the distribution ofhuman judgements is still an open, challenging problem with a large room forimprovements. We showcase the common errors for MC Dropout and Re-Calibration.Finally, we give guidelines on the usage of these methods with different levelsof data availability and encourage future work on modeling the human opiniondistribution for language reasoning. Our code and data are publicly availableat https://github.com/easonnie/ChaosNLI

Distributed NLI: Learning to Predict Human Opinion Distributions for Language Reasoning