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 a graph-aware autoencoder ensemble framework, with associatedformalisms and tooling, designed to facilitate deep learning for scholarship inthe humanities. By composing sub-architectures to produce a model isomorphic toa humanistic domain we maintain interpretability while providing functionsignatures for each sub-architectural choice, allowing both traditional andcomputational researchers to collaborate without disrupting establishedpractices. We illustrate a practical application of our approach to ahistorical study of the American post-Atlantic slave trade, and make severalspecific technical contributions: a novel hybrid graph-convolutionalautoencoder mechanism, batching policies for common graph topologies, andmasking techniques for particular use-cases. The effectiveness of the frameworkfor broadening participation of diverse domains is demonstrated by a growingsuite of two dozen studies, both collaborations with humanists and establishedtasks from machine learning literature, spanning a variety of fields and datamodalities. We make performance comparisons of several different architecturalchoices and conclude with an ambitious list of imminent next steps for thisresearch.

Graph-Convolutional Autoencoder Ensembles for the Humanities, Illustrated with a Study of the American Slave Trade