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

Hierarchical models are utilized in a wide variety of problems which arecharacterized by task hierarchies, where predictions on smaller subtasks areuseful for trying to predict a final task. Typically, neural networks are firsttrained for the subtasks, and the predictions of these networks aresubsequently used as additional features when training a model and doinginference for a final task. In this work, we focus on improving learning forsuch hierarchical models and demonstrate our method on the task of speakertrait prediction. Speaker trait prediction aims to computationally identifywhich personality traits a speaker might be perceived to have, and has been ofgreat interest to both the Artificial Intelligence and Social Sciencecommunities. Persuasiveness prediction in particular has been of interest, aspersuasive speakers have a large amount of influence on our thoughts, opinionsand beliefs. In this work, we examine how leveraging the relationship betweenrelated speaker traits in a hierarchical structure can help improve our abilityto predict how persuasive a speaker is. We present a novel algorithm thatallows us to backpropagate through this hierarchy. This hierarchical modelachieves a 25% relative error reduction in classification accuracy over currentstate-of-the art methods on the publicly available POM dataset.

Preserving Intermediate Objectives: One Simple Trick to Improve Learning for Hierarchical Models