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

In this work, we unify several existing decoding strategies for punctuationprediction in one framework and introduce a novel strategy which utilisesmultiple predictions at each word across different windows. We show thatsignificant improvements can be achieved by optimising these strategies aftertraining a model, only leading to a potential increase in inference time, withno requirement for retraining. We further use our decoding strategy frameworkfor the first comparison of tagging and classification approaches forpunctuation prediction in a real-time setting. Our results show that aclassification approach for punctuation prediction can be beneficial whenlittle or no right-side context is available.

Mask-combine Decoding and Classification Approach for Punctuation Prediction with real-time Inference Constraints