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

There have been many recent investigations into prompt-based training oftransformer language models for new text genres in low-resource settings. Theprompt-based training approach has been found to be effective in generalizingpre-trained or fine-tuned models for transfer to resource-scarce settings. Thiswork, for the first time, reports results on adopting prompt-based training oftransformers for \textit{scholarly knowledge graph object prediction}. The workis unique in the following two main aspects. 1) It deviates from the otherworks proposing entity and relation extraction pipelines for predicting objectsof a scholarly knowledge graph. 2) While other works have tested the method ontext genera relatively close to the general knowledge domain, we test themethod for a significantly different domain, i.e. scholarly knowledge, in turntesting the linguistic, probabilistic, and factual generalizability of theselarge-scale transformer models. We find that (i) per expectations, transformermodels when tested out-of-the-box underperform on a new domain of data, (ii)prompt-based training of the models achieve performance boosts of up to 40\% ina relaxed evaluation setting, and (iii) testing the models on a starklydifferent domain even with a clever training objective in a low resourcesetting makes evident the domain knowledge capture gap offering anempirically-verified incentive for investing more attention and resources tothe scholarly domain in the context of transformer models.

Evaluating Prompt-based Question Answering for Object Prediction in the Open Research Knowledge Graph