Deep learning for noise-tolerant RDFS reasoning

Tracking #: 1866-3079

This paper is currently under review
Bassem Makni
James Hendler

Responsible editor: 
Guest Editors Semantic Deep Learning 2018

Submission type: 
Full Paper
Since the introduction of the Semantic Web vision in 2001 as an extension to the Web, the main research focus in semantic reasoning was on the soundness and completeness of the reasoners. While these reasoners assume the veracity of the input data, the reality is that the Web of data is inherently noisy. Recent research work on semantic reasoning with noise-tolerance focuses on type inference and does not aim for full RDFS reasoning. This paper documents a novel approach that takes previous research efforts in noise-tolerance in the Semantic Web to the next level of full RDFS reasoning by utilizing advances in deep learning research. This is a stepping stone towards bridging the Neural-Symbolic gap for RDFS reasoning which is accomplished through layering RDF graphs and encoding them in the form of 3D adjacency matrices where each layer layout forms a graph word. Every input graph and its corresponding inference are then represented as sequences of graph words. The RDFS inference becomes equivalent to the translation of graph words that is achieved through neural network translation. The evaluation confirms that deep learning can in fact be used to learn RDFS rules from both synthetic and real-world Semantic Web data while showing noise-tolerance capabilities as opposed to rule-based reasoners.
Full PDF Version: 
Under Review


Is Figure 6: 3D Adjacency matrix on page 12 missing?

Yes, thanks for the observation!

I uploaded the figure here: