Deep Learning for Noise-Tolerant RDFS Reasoning

Printer-friendly version

Abstract:

Since the introduction of the Semantic Web vision in 2001 as an extension to the Web, where machines can reason about the content, the main research focus in semantic reasoning was on the soundness and completeness of the reasoners. These reasoners also assume the veracity of the input data while the Web of data is inherently noisy. In 2010, Hitzler and van Harmelen called for questioning the model-theoretic semantic reasoning and investigation of machine learning (ML) for semantic reasoning [1] as ML techniques are more robust to noisy data. Four years later, a position paper about machine learning on linked data [2] considered the research efforts to couple both fields still ”disappointing”.

Recent research work on semantic reasoning with noise-tolerance focuses on type inference and does not aim for full RDFS reasoning. This thesis 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. Deep learning techniques- even though robust to noise and very effective in generalizing across a number of fields including machine vision, natural language understanding, speech recognition etc. - require large amounts of data of low-level representations rather than “symbolic representations used in knowledge representation” ([3]). This challenge constitutes what we refer to as the Neural-Symbolic gap.

This thesis aims to provide a stepping stone towards bridging the Neural-Symbolic gap specifically in the Semantic Web field and RDFS reasoning in particular. This is accomplished through layering Resource Description Framework (RDF) graphs and encoding them in the form of 3D adjacency matrices. Each layer layout in the 3D adjacency matrices form what termed as graph word. Every input graph and its corresponding inference are then represented as sequences of graph words. The RDFS inference becomes equivalent to graph words translation 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 as well as real-world Semantic Web data while showing noise-tolerance capabilities compared to rule-based reasoners.

  1. P. Hitzler and F. van Harmelen, “A reasonable semantic web,” Semantic Web, vol. 1, no. 1, 2, pp. 39–44, 2010.
  2. P. Bloem and G. K. De Vries, “Machine learning on linked data, a position paper,” Linked Data for Knowledge Discovery, p. 69, 2014.
  3. A. Garcez, T. R. Besold, L. De Raedt, P. Földiak, P. Hitzler, T. Icard, K.-U. Kühnberger, L. C. Lamb, R. Miikkulainen, and D. L. Silver, “Neural-symbolic learning and reasoning: Contributions and challenges,” 2015.

History

DateCreated ByLink
August 29, 2018
23:31:30
Bassem MakniDownload