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

Link prediction is an important task in addressing the incompleteness problemof knowledge graphs (KG). Previous link prediction models suffer from issuesrelated to either performance or explanatory capability. Furthermore, modelsthat are capable of generating explanations, often struggle with erroneouspaths or reasoning leading to the correct answer. To address these challenges,we introduce a novel Neural-Symbolic model named FaSt-FLiP (stands for Fast andSlow Thinking with Filtered rules for Link Prediction task), inspired by twodistinct aspects of human cognition: "commonsense reasoning" and "thinking,fast and slow." Our objective is to combine a logical and neural model forenhanced link prediction. To tackle the challenge of dealing with incorrectpaths or rules generated by the logical model, we propose a semi-supervisedmethod to convert rules into sentences. These sentences are then subjected toassessment and removal of incorrect rules using an NLI (Natural LanguageInference) model. Our approach to combining logical and neural models involvesfirst obtaining answers from both the logical and neural models. These answersare subsequently unified using an Inference Engine module, which has beenrealized through both algorithmic implementation and a novel neural modelarchitecture. To validate the efficacy of our model, we conducted a series ofexperiments. The results demonstrate the superior performance of our model inboth link prediction metrics and the generation of more reliable explanations.

Emulating the Human Mind: A Neural-symbolic Link Prediction Model with Fast and Slow Reasoning and Filtered Rules