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

Prompt-based classifiers are an attractive approach for zero-shotclassification. However, the precise choice of the prompt template and labelwords can largely influence performance, with semantically equivalent settingsoften showing notable performance difference. This discrepancy can be partlyattributed to word biases, where the classifier may be biased towards classes.To address this problem, it is possible to optimise classification thresholdson a labelled data set, however, this mitigates some of the advantages ofprompt-based classifiers. This paper instead approaches this problem byexamining the expected marginal probabilities of the classes. Here,probabilities are reweighted to have a uniform prior over classes, in anunsupervised fashion. Further, we draw a theoretical connection between theclass priors and the language models' word prior, and offer the ability to seta threshold in a zero-resource fashion. We show that matching class priorscorrelates strongly with the oracle upper bound performance and demonstratelarge consistent performance gains for prompt settings over a range of NLPtasks.

Mitigating Word Bias in Zero-shot Prompt-based Classifiers