Lidé

Mgr. Miroslav Blaško, Ph.D.

Všechny publikace

Entity Linking and Lexico-Semantic Patterns for Ontology Learning

  • DOI: 10.1007/978-3-030-49461-2_9
  • Odkaz: https://doi.org/10.1007/978-3-030-49461-2_9
  • Pracoviště: Katedra počítačů, Skupina znalostních softwarových systémů
  • Anotace:
    Ontology learning from a text written in natural language is a well-studied domain. However, the applicability of techniques for ontology learning from natural language texts is strongly dependent on the characteristics of the text corpus and the language used. In this paper, we present our work so far in entity linking and enhancing the ontology with extracted relations between concepts. We discuss the benefits of adequately designed lexico-semantic patterns in ontology learning. We propose a preliminary set of lexico-semantic patterns designed for the Czech language to learn new relations between concepts in the related domain ontology in a semi-supervised approach. We utilize data from the urban planning and development domain to evaluate the introduced technique. As a partial prototypical implementation of the stack, we present Annotace, a text annotation service that provides links between the ontology model and the textual documents in Czech.

TermIt: A Practical Semantic Vocabulary Manager

  • DOI: 10.5220/0009563707590766
  • Odkaz: https://doi.org/10.5220/0009563707590766
  • Pracoviště: Katedra počítačů, Skupina znalostních softwarových systémů
  • Anotace:
    Many organizations already benefit from using semantic vocabularies which help them systematize, search and reuse their data. However, to efficiently manage such vocabularies, appropriate and adequate tools are needed. In this paper, we present TermIt, an integrated system for managing a set of interconnected vocabularies, identification of individual concepts in source documents, and using such terms for semantic data asset annotation and subsequent search. We relate TermIt to other relevant tools and present usage scenarios we have identified so far.

Ontology-based Dataset Exploration -- A Temporal Ontology Use-Case

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Datasets are created in the linked data ecosystem with varying data and metadata quality. Shallow (or poor-quality) metadata prevent dataset provision services (CKAN catalogs, etc.) from supporting their users in efficient search and exploration of datasets they need. In this paper we approach the problem by formalizing the dataset exploration scenario, introducing the notion of ontology-based dataset descriptors. We present a particular use-case of creating temporal dataset descriptors and their application in the field of Czech Open Data cloud. We also discuss practical problems that we came across during descriptor extraction. Experimental datasets and computed descriptors are published in a public SPARQL endpoint.

A Diagnostic Ontological Model for Damages to Historical Constructions

  • Autoři: Cacciotti, R., Mgr. Miroslav Blaško, Ph.D., Valach, J.
  • Publikace: Journal of Cultural Heritage. 2015, 16(1), 40-48. ISSN 1296-2074.
  • Rok: 2015
  • DOI: 10.1016/j.culher.2014.02.002
  • Odkaz: https://doi.org/10.1016/j.culher.2014.02.002
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Understanding damages to cultural heritage represents a very complex task based on a multidisciplinary interpretation of gathered information. Integrating the knowledge of different branches of science related to cultural heritage protection into a comprehensive knowledge-based system allows endorsing professional decision-making processes with the particular scope to mitigate the challenge posed by damage diagnosis to both expert and non-expert users. This paper proposes a model attempting to convey the benefits of modern ontological know-how to the management and processing of information concerning the diagnostic phase. The methodology consists in translating the professional approach to diagnosis of damages into a computer readable form able to replicate the assessment procedure, step by step, towards a feasible intervention. An overview of possible applications to conservation practice, such as the development of a mobile application dedicated to damage surveying and assessment, is also presented.

Efficient Exploration of Linked Data Cloud

  • DOI: 10.5220/0005558002550261
  • Odkaz: https://doi.org/10.5220/0005558002550261
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    As the size of semantic data available as Linked Open Data (LOD) increases, the demand for methods for automated exploration of data sets grows as well. A data consumer needs to search for data sets meeting his interest and look into them using suitable visualization techniques to check whether the data sets are useful or not. In the recent years, particular advances have been made in the field, e.g., automated ontology matching techniques or LOD visualization platforms. However, an integrated approach to LOD exploration is still missing. On the scale of the whole web, the current approaches allow a user to discover data sets using keywords or manually through large data catalogs. Existing visualization techniques presume that a data set is of an expected type and structure. The aim of this position paper is to show the need for time and space efficient techniques for discovery of previously unknown LOD data sets on the base of a consumer’s interest and their automated visualization which we address in our ongoing work.

Ontology Evolution Using Ontology Templates

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Evolving ontologies by domain experts is difficult and typically cannot be performed without the assistance of an ontology engineer. This process takes long time and often recurrent modeling errors have to be resolved. This paper proposes a technique for creating controlled ontology evolution scenarios that ensure consistency of the possible ontology evolution and give guarrantees to the domain expert that his/her updates do not cause inconsistency. We introduce ontology templates that formalize the notion of controlled evolution and define ontology template consistency checking service together with a consistency checking algorithm. We prove correctness and demonstate the practical use of the techniques in two scenarios.

Introduction to an Ontology-Driven Documentation System of Damages to Cultural Heritage

  • DOI: 10.1260/2047-4970.3.2.255
  • Odkaz: https://doi.org/10.1260/2047-4970.3.2.255
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Deriving from the complex nature of cultural heritage conservation and its heterogeneous tasks it is the need for enhancing a systematic but flexible organization of expert knowledge in the field. Such organization should address comprehensively the interrelations and complementariness among the different factors that come into play in the understanding of diagnostic and intervention problems. The purpose of the system introduced in this paper, called MONDIS, is to endorse this kind of organization. The system allows replicating in a computer readable form the basic dependence among factors influencing the description, diagnosis and intervention of damages to immovable objects. More specifically MONDIS allows to input and search entries concerning object description, structural evolution, location characteristics and risk, component, material properties, surveys and measurements, damage typology, damage triggering events and possible interventions. The system supports searching features typical of standard databases, as it allows for the digitalization of a wide range of information including professional reports, books, articles and scientific papers. It also allows for computer aided retrieval of information tailored to user's requirements. The approach consists in formalising an ontological representation of the field of heritage conservation compatible with the professional approach commonly employed to processing of data. The paper also presents a series of applications which run on such ontology, including a web-based interface for data inputting, a terminology editor for defining and searching a pictographic glossary of all terms stored in the system, a knowledge matrix for browsing the cause-effect relationships in damage formation together with insights on possible interventions and a mobile application for supporting in-situ condition assessment of buildings.

MONDIS: Using Ontologies for Monument Damage Descriptions

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    The MONDIS project is aimed at knowledge management in the field of monument conservation, monument damages and related interventions. The IT platform developed within the project is to be used by conservators, monument owners and other stakeholders to share their terminology, contextual knowledge, as well as experience about existing damages and their interventions.

Monument Damage Information System (MONDIS): An Ontological Approach to Cultural Heritage Documentation

  • Autoři: Cacciotti, R., Valach, J., Kuneš, P., Čerňanský, M., Ing. Petr Křemen, Ph.D., Mgr. Miroslav Blaško, Ph.D.,
  • Publikace: ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences. Göttingen: Copernicus GmbH, 2013. p. 55-60. ISSN 2194-9042.
  • Rok: 2013
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Deriving from the complex nature of cultural heritage conservation it is the need for enhancing a systematic but flexible organization of expert knowledge in the field. Such organization should address comprehensively the interrelations and complementariness among the different factors that come into play in the understanding of diagnostic and intervention problems. The purpose of MONDIS is to endorse this kind of organization. The approach consists in applying an ontological representation to the field of heritage conservation in order to establish an appropriate processing of data. The system allows replicating in a computer readable form the basic dependence among factors influencing the description, diagnosis and intervention of damages to immovable objects. More specifically MONDIS allows to input and search entries concerning object description, structural evolution, location characteristics and risk, component, material properties, surveys and measurements, damage typology, damage triggering events and possible interventions. The system supports searching features typical of standard databases, as it allows for the digitalization of a wide range of information including professional reports, books, articles and scientific papers. It also allows for computer aided retrieval of information tailored to user's requirements. The foreseen outputs will include a web user interface and a mobile application for visual inspection purposes.

Monument Damage Ontology

  • DOI: 10.1007/978-3-642-34234-9_22
  • Odkaz: https://doi.org/10.1007/978-3-642-34234-9_22
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Capturing knowledge about damages and failures of culture heritage objects is a complex task because of term ambiguity, knowledge incompleteness and variety. To tackle this complexity, the paper introduces a semantic web ontology that aims at modeling monument damage knowledge with significant contextual information, including monument identification, damage identification, risk assessment, damage diagnosis and remedial measures. The developed ontology is being tested in the MONDIS project as a background knowledge for custom software tools for management of damage failure knowledge. During the course of the project it becomes a common model for linked-data-compliant knowledge-based system serving different stakeholders to model/retrieve/compare different cases of damage and successful interventions.

Ontology-Driven Mindmapping

  • Autoři: Ing. Petr Křemen, Ph.D., Mička, P., Mgr. Miroslav Blaško, Ph.D., Šmíd, M.
  • Publikace: Proceedings of the 8th International Conference on Semantic Systems. New York: ACM, 2012, pp. 125-132. ISBN 978-1-4503-1112-0. Available from: http://dl.acm.org/citation.cfm?id=2362517
  • Rok: 2012
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Mindmaps have been a popular means for intuitive and user-friendly conceptual modeling for several years. This paper proposes a mindmapping tool driven by semantic web ontologies that allows to assign meanings to the mindmap nodes and, even more importantly, guide the user through mindmap creation by proposing ontological concepts and roles relevant to each mindmap node. The tool is backed by OWL ontologies that allow to capture domain knowledge semantics precisely and rigorously. The tool is being developed as a part of the MONDIS project aimed at efficient knowledge management of immovable cultural heritage failures records. As such, the tool is currently used by civil engineering experts for collaborative authoring of structural damage records.

Knowledge Modelling to Support Inquiry Learning Tasks

  • Autoři: Wolf, A., Mulholland, P., Zdráhal, Z., Mgr. Miroslav Blaško, Ph.D.,
  • Publikace: Lecture Notes in Computer Science. Berlin: Springer, 2010, pp. 198-209. ISSN 0302-9743. ISBN 978-3-642-15280-1.
  • Rok: 2010
  • DOI: 10.1007/978-3-642-15280-1_20
  • Odkaz: https://doi.org/10.1007/978-3-642-15280-1_20
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    In this paper we describe the SILVER toolkit, which is designed for tasks in which a user learns by analysing and interpreting a set of resources. The user categorises each resource according to the set of properties that they identify as being applicable to it. Due to the large amount of data generated by this type of task, the user may find it hard to identify patterns in their classification and tagging, to recognise their own inconsistencies or make comparisons between themselves and others. In the first SILVER task described, the ID3 decision tree algorithm is applied to the user's data to identify patterns and generate different types of feedback. Principles of spatial hypertext are used to produce an interactive visualization of the summarized data. As the user interacts with the resources, they can see their progress and changing perspective on the task.

Participatory Design of Netcarity Services Using Different Perspectives

  • Autoři: Bierhoff, I., Goosen, B., Wintjens, K., Huijnen, C., Ing. Petr Křemen, Ph.D., Kouba, Z., Válek, F., Šmíd, M., Mgr. Miroslav Blaško, Ph.D., Panis, P.
  • Publikace: Proceedings of the first International AEGIS Conference. Seville: AEGIS project, 2010, pp. 202-209. Available from: http://www.epr.eu/aegis/wp-content/uploads/2011/02/Conference_Proceedings.pdf
  • Rok: 2010
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    The road towards implementing technology and services developed in research projects is often a bumpy one. Developing in a controlled lab environment requires another type of expertise than implementing technology in real-life situations. However when the two types of expertise are combined during the research phase they can benefit from each other and achieve good results. For that other types of skills, such as communicative skills and expertise in working in a multidisciplinary team are also required. This paper gives insight into the approach taken in the Netcarity project to being able to deliver services in real homes.

Privacy Protection Using Semantic Technologies

  • Autoři: Mgr. Miroslav Blaško, Ph.D., Ing. Petr Křemen, Ph.D., Kouba, Z.
  • Publikace: Proceedings of the Twentieth European Meeting on Cybernetics and Systems Research. Vienna: Austrian Society for Cybernetics Studies, 2010, pp. 585-590. ISBN 978-3-85206-178-8.
  • Rok: 2010
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    This paper presents a novel semantic framework for authoring privacy policies of servers and privacy preferences of clients as well as their matching. The proposed solution allows for interactive detection and explanation of semantic inconsistencies during policy/preferences design. Privacy policies are expressed as OWL-DL ontologies and privacy preferences as OWL-DL integrity constraints checked via SPARQL-DL queries. The well-defined semantics of our solution together with flexibility of semantic technologies fixes known serious problems of P3P and APPEL matching scenario, including ambiguity and semantical incorrectness.

Semantic Annotation of Objects

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Compared to traditional ways of annotating multimedia resources (textual documents, photographs, audio/video clips etc.) by keywords in form of text fragments, semantic annotations are based on tagging such multimedia resources with meaning of objects (like cultural/historical artifacts) the resource is dealing with. The search for multimedia resources stored in a repository enriched with semantic annotations makes use of an appropriate reasoning algorithm. Knowledge management and Semantic Web communities have developed a number of relevant formalisms and methods. This chapter is motivated by practical experience with authoring of semantic annotations of cultural heritage related resources/objects.

Semantic Approach to Privacy Protection

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    P3P is a W3C recommendation for expressing service privacy practices in a structured computer-readable form. However, the lack of formal semantics makes it inconvenient for fully computerized matching against privacy preferences (e.g. the APPEL language). SemPref is an interesting approach that defines several possible semantics for P3P using relational database technology. However, it still doesn't have capabilities to detect errors that frequently occur when designing both privacy preferences and service privacy practices. This paper analyses the problem of detecting semantic errors in P3P policies in depth and proposes a solution based on semantic technologies.P3P is a W3C recommendation for expressing service privacy practices in a structured computer-readable form. However, the lack of formal semantics makes it inconvenient for fully computerized matching against privacy preferences (e.g. the APPEL language).

Za stránku zodpovídá: Ing. Mgr. Radovan Suk