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

In NLP, incremental processors produce output in instalments, based onincoming prefixes of the linguistic input. Some tokens trigger revisions,causing edits to the output hypothesis, but little is known about why modelsrevise when they revise. A policy that detects the time steps where revisionsshould happen can improve efficiency. Still, retrieving a suitable signal totrain a revision policy is an open problem, since it is not naturally availablein datasets. In this work, we investigate the appropriateness of regressionsand skips in human reading eye-tracking data as signals to inform revisionpolicies in incremental sequence labelling. Using generalised mixed-effectsmodels, we find that the probability of regressions and skips by humans canpotentially serve as useful predictors for revisions in BiLSTMs and Transformermodels, with consistent results for various languages.

Revising with a Backward Glance: Regressions and Skips during Reading as Cognitive Signals for Revision Policies in Incremental Processing