We analyse perception and memory using mathematical models for knowledge graphs and tensors to gain insights in the corresponding functionalities of the human mind. Our discussion is based on the concept of propositional sentences consisting of \textit{subject-predicate-object} (SPO) triples for expressing elementary facts. SPO sentences are the basis for most natural languages but might also be important for explicit perception and declarative memories, as well as intra-brain communication and the ability to argue and reason. A set of SPO sentences can be described as a knowledge graph, which can be transformed into an adjacency tensor. We introduce tensor models, where concepts have dual representations as indices and associated embeddings, two constructs we believe are essential for the understanding of implicit and explicit perception and memory in the brain. We argue that a biological realization of perception and memory imposes constraints on information processing. In particular, we propose that explicit perception and declarative memories require a semantic decoder, which, in a simple realization, is based on four layers: First, a sensory memory layer, as a buffer for sensory input, second, an index layer representing concepts, third, a memoryless representation layer for the broadcasting of information and fourth, a working memory layer as a processing center and data buffer. In a Bayesian brain interpretation, semantic memory defines the prior for triple statements. We propose that, in evolution and during development, semantic memory, episodic memory and natural language evolved as emergent properties in the agents' process to gain deeper understanding of sensory information. We present a concrete model realization and validate some aspects of our proposed model on benchmark data where we demonstrate state-of-the-art performance.

Recent advancements in audio event classification often ignore the structure and relation between the label classes available as prior information. This structure can be defined by ontology and augmented in the classifier as a form of domain knowledge. To capture such dependencies between the labels, we propose an ontology-aware neural network containing two components: feed-forward ontology layers and graph convolutional networks (GCN). The feed-forward ontology layers capture the intra-dependencies of labels between different levels of ontology. On the other hand, GCN mainly models inter-dependency structure of labels within an ontology level. The framework is evaluated on two benchmark datasets for single-label and multi-label audio event classification tasks. The results demonstrate the proposed solutions efficacy to capture and explore the ontology relations and improve the classification performance.

Primary obligations include obtaining explicit consent from the data subject for the processing of personal data and providing full transparency with respect to processing and sharing. With the coming into effect of the GDPR in May 2018, several tools [11, 16, 19] have recently been developed that can be used to assist companies to assess the compliance of their systems and processes with respect to obligations set forth in the GDPR. However, such tools are targeted at self assessment (i.e. companies complete standard questionnaires in the form of a privacy impact assessment) and cannot be used to automatically check compliance with usage constraints. Such, automated transparency and compliance mechanisms would require not only machine-readable representations of the users consent, but also machine-readable representations of data processing and sharing. SPECIAL 1 is an EU H2020 research and innovation action, which addresses these challenges by demonstrating how Semantic Web technologies can be used for both consent and personal data processing representation and compliance checking. In particular we devise a suite of ontologies and vocabularies that can be used to: (i) model data usage policies, conforming the SPECIAL's Usage Policy Language, (ii) represent data processing and sharing events in a semantic log. Both of which have been developed in close collaboration with legal experts, thus ensuring that our automated compliance checking is tightly coupled with the legal assessment process.1 https://www.specialprivacy.eu/ 1 arXiv:2001.09461v1

Knowledge bases (KBs) are not static entities: new information constantly appears and some of the previous knowledge becomes obsolete. In order to reflect this evolution of knowledge, KBs should be expanded with the new knowledge and contracted from the obsolete one. This problem is well-studied for propositional but much less for first-order KBs. In this work we investigate knowledge expansion and contraction for KBs expressed in DL-Lite, a family of description logics (DLs) that underlie the tractable fragment OWL 2 QL of the Web Ontology Language OWL 2. We start with a novel knowledge evolution framework and natural postulates that evolution should respect, and compare our postulates to the well-established AGM postulates. We then review well-known model and formula-based approaches for expansion and contraction for propositional theories and show how they can be adapted to the case of DL-Lite. In particular, we show intrinsic limitations of model-based approaches: besides the fact that some of them do not respect the postulates we have established, they ignore the structural properties of KBs. This leads to undesired properties of evolution results: evolution of DL-Lite KBs cannot be captured in DL-Lite. Moreover, we show that well-known formula-based approaches are also not appropriate for DL-Lite expansion and contraction: they either have a high complexity of computation, or they produce logical theories that cannot be expressed in DL-Lite. Thus, we propose a novel formula-based approach that respects our principles and for which evolution is expressible in DL-Lite. For this approach we also propose polynomial time deterministic algorithms to compute evolution of DL-Lite KBs when evolution affects only factual data.

We study complete approximations of an ontology formulated in a non-Horn description logic (DL) such as $\mathcal{ALC}$ in a Horn DL such as~$\mathcal{EL}$. We provide concrete approximation schemes that are necessarily infinite and observe that in the $\mathcal{ELU}$-to-$\mathcal{EL}$ case finite approximations tend to exist in practice and are guaranteed to exist when the original ontology is acyclic. In contrast, neither of this is the case for $\mathcal{ELU}_\bot$-to-$\mathcal{EL}_\bot$ and for $\mathcal{ALC}$-to-$\mathcal{EL}_\bot$ approximations. We also define a notion of approximation tailored towards ontology-mediated querying, connect it to subsumption-based approximations, and identify a case where finite approximations are guaranteed to exist.

Ea ch process description is shaped like a formalized business policy consisting of the following set of features: - the file(s) to be processed; - the software that carries out the processing; - the purpose of the processing; - the entities that can access the results of the processing; - the details of where the results are stored and for how long; - the obligations that are fulfilled while (or before) carrying out the processing; - the legal basis of the processing. It is not hard to see that the first five elements in the above list match SPECIAL's usage policy language (UPL) introduced in Section 3. As far as the above elements are concerned, the only difference between UPL expressions and a business policy is the granularity of attribute values. Fo r example, the involved data (specified in the first element of the above list) are not expressed as a general, content-oriented category, but rather as a concrete set of data sourc es or data items. Such objects can be modeled as instances or subclasses of the general data categories illustrated in Section 3, thereby creating a link between digital artifacts and usage policies. Similar considerations hold for the other a t-tributes: - processing is not necessarily described in the abstract terms adopted by the processing vocabulary introduced in Section 3; in a business policy, this can be specified by naming concrete software procedures; - the purpose of data processing may be directly related to the data controller's mission and products; - recipients may consist of a concrete list of legal and/or physical persons, as opposed to general categories such as Ours or ThirdParty; - storage may be specified by a list of specific data repositories, at the level of files and hosts. With this level of granularity, specific authorizations can be derived from the business policy, for example: The indicated software procedure can read the indicated data sources. The results can be written in the specified repositories. The specified recipients can read the repositories...

Wikipedia is a huge opportunity for machine learning, being the largest semi-structured base of knowledge available. Because of this, many works examine its contents, and focus on structuring it in order to make it usable in learning tasks, for example by classifying it into an ontology. Beyond its textual contents, Wikipedia also displays a typical graph structure, where pages are linked together through citations. In this paper, we address the task of integrating graph ( i.e. structure) information to classify Wikipedia into a fine-grained named entity ontology (NE), the Extended Named Entity hierarchy. To address this task, we first start by assessing the relevance of the graph structure for NE classification. We then explore two directions, one related to feature vectors using graph descriptors commonly used in large-scale network analysis, and one extending flat classification to a weighted model taking into account semantic similarity. We conduct at-scale practical experiments, on a manually labeled subset of 22,000 pages extracted from the Japanese Wikipedia. Our results show that integrating graph information succeeds at reducing sparsity of the input feature space, and yields classification results that are comparable or better than previous works.

A person ontology comprising concepts, attributes and relationships of people has a number of applications in data protection, de-identification, population of knowledge graphs for business intelligence and fraud prevention. While artificial neural networks have led to improvements in Entity Recognition, Entity Classification, and Relation Extraction, creating an ontology largely remains a manual process, because it requires a fixed set of semantic relations between concepts. In this work, we present a system for automatically populating a person ontology graph from unstructured data using neural models for Entity Classification and Relation Extraction. We introduce a new dataset for these tasks and discuss our results. Introduction We can define Personal Data Entity (PDE) as any information about a person.

We address the problem of handling provenance information in ELHr ontologies. We consider a setting recently introduced for ontology-based data access, based on semirings and extending classical data provenance, in which ontology axioms are annotated with provenance tokens. A consequence inherits the provenance of the axioms involved in deriving it, yielding a provenance polynomial as an annotation. We analyse the semantics for the ELHr case and show that the presence of conjunctions poses various difficulties for handling provenance, some of which are mitigated by assuming multiplicative idempotency of the semiring. Under this assumption, we study three problems: ontology completion with provenance, computing the set of relevant axioms for a consequence, and query answering.

Clinical decision support systems combine knowledge and data from a variety of sources, represented by quantitative models based on stochastic methods, or qualitative based rather on expert heuristics and deductive reasoning. At the same time, case-based reasoning (CBR) memorizes and returns the experience of solving similar problems. The cooperation of heterogeneous clinical knowledge bases (knowledge objects, semantic distances, evaluation functions, logical rules, databases...) is based on medical ontologies. A multi-agent decision support system (MADSS) enables the integration and cooperation of agents specialized in different fields of knowledge (semiology, pharmacology, clinical cases, etc.). Each specialist agent operates a knowledge base defining the conduct to be maintained in conformity with the state of the art associated with an ontological basis that expresses the semantic relationships between the terms of the domain in question. Our approach is based on the specialization of agents adapted to the knowledge models used during the clinical steps and ontologies. This modular approach is suitable for the realization of MADSS in many areas.