AIFeb 10, 2020

Explainable Deep RDFS Reasoner

arXiv:2002.03514v14 citations
Originality Incremental advance
AI Analysis

This work addresses the explainability gap for users of neural-symbolic systems, though it builds incrementally on existing graph word approaches.

The paper tackles the lack of explainability in deep learning-based RDFS reasoners by introducing a neural network model that outputs derivations for inferred triples, achieving validation accuracies as high as 96% on synthetic and real-world datasets.

Recent research efforts aiming to bridge the Neural-Symbolic gap for RDFS reasoning proved empirically that deep learning techniques can be used to learn RDFS inference rules. However, one of their main deficiencies compared to rule-based reasoners is the lack of derivations for the inferred triples (i.e. explainability in AI terms). In this paper, we build on these approaches to provide not only the inferred graph but also explain how these triples were inferred. In the graph words approach, RDF graphs are represented as a sequence of graph words where inference can be achieved through neural machine translation. To achieve explainability in RDFS reasoning, we revisit this approach and introduce a new neural network model that gets the input graph--as a sequence of graph words-- as well as the encoding of the inferred triple and outputs the derivation for the inferred triple. We evaluated our justification model on two datasets: a synthetic dataset-- LUBM benchmark-- and a real-world dataset --ScholarlyData about conferences-- where the lowest validation accuracy approached 96%.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes