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

Learned knowledge graph representations supporting robots contain a wealth ofdomain knowledge that drives robot behavior. However, there does not exist aninference reconciliation framework that expresses how a knowledge graphrepresentation affects a robot's sequential decision making. We use apedagogical approach to explain the inferences of a learned, black-boxknowledge graph representation, a knowledge graph embedding. Our interpretablemodel, uses a decision tree classifier to locally approximate the predictionsof the black-box model, and provides natural language explanationsinterpretable by non-experts. Results from our algorithmic evaluation affirmour model design choices, and the results of our user studies with non-expertssupport the need for the proposed inference reconciliation framework.Critically, results from our simulated robot evaluation indicate that ourexplanations enable non-experts to correct erratic robot behaviors due tononsensical beliefs within the black-box.

Explainable Knowledge Graph Embedding: Inference Reconciliation for Knowledge Inferences Supporting Robot Actions