Toward a taxonomy of concepts using web documents structure

Zarrad, Rim; Doggaz, Narjes; Zagrouba, Ezzeddine

doi:10.1145/2428736.2428762

Cited by 3 publications

(2 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, for each building at the campus, an Extended Ontology is used, to keep the uniqueness of location and device information. Hierarchy is used for Ontology Model, which depends on analysis of relevant concepts in terms of entities and integrated data of BIM [16]. In taxonomic relations, links are established on canonical structure of concepts and lexico-syntactic patterns [17] are used to construct unique Ids for meaningful Ontology according to BMS and BIM.…”

Section: Extending Ontology Modelmentioning

confidence: 99%

Smart Building: SemanticWeb Technology Services for BIM (Location and Device Information)

Pitner

Asfand-e-yar

Kučera

2014

European IST Projects - The Quest for Excellence Towards 2020

View full text Add to dashboard Cite

Smart Building aims to autonomously control devices and systems in given environment. These application systems are nevertheless supervised by facility management. The facility management normally is aided by heterogeneous application systems. Due to multifarious data of the systems, applications, and missing integration of data in building automation, the data is manually collected by facility management, for analysis and decision making. Therefore, such a system is required to integrate the multi-form data of various systems and applications. Hence, Semantic Web technology is proposed in this paper to integrate data and to implement front end. Therefore, Semantic Web technology not only provide base for analysis and decision making for facility management, but also facilitate developers to focus on front-end application. The aim is to structure the data, where active devices cannot only be located in a building but also identify according to its connected systems and subsystems. incorporate a wide scale of automated systems, such as security system, access control system, fire alarm system or building automation systems that controls Heating, Ventilation, Air Conditioning (HVAC) devices. Building Management System (BMS) facilitates remote monitoring and controlling of the building operations. The detailed description of CAFM and BMS software can be found in [1,2].Currently the integration of BMS data with CAFM and BIM is simplified, which is not effectively queried because the integration is missing. The integration between them is impossible, without semantic structure because BMS data is determined by network topology. The semantic structure is required for the advanced analytical features of CAFM software, which are currently not integrated with BMS data. The missing integration between CAFM, BMS and BIM does not affect small sites with less installation, as long as data collection and analysis are performed manually. However, for large sites (i.e. installation of hundreds of devices, thousands of sensors), manual data collection prevents effective gathering of required information. Despite of large sites, BMS contains large amount of accurate, up-to-date and detailed data which is valuable for building operation analysis. This data cannot be collected by any other way, other than semantic structure (i.e. designing Ontology Model).Currently the integration of BMS data with CAFM and BIM is simplified to a simple structure that cannot be effectively queried because the integration part is completely missing. The integration is impossible because BMS data structure is determined by the network topology, not by the semantic structure. The semantic structure is required because the advanced analytical features of CAFM software are currently not integrated with for BMS data. This does not affect the small installations, where data retrieval and analysis can be easily performed manually. However, for large sites (hundreds of devices, thousands of sensors), the amount of data prevents effective gathering of required...

show abstract

Section: Extending Ontology Modelmentioning

confidence: 99%

Smart Building: SemanticWeb Technology Services for BIM (Location and Device Information)

Pitner

Asfand-e-yar

Kučera

2014

European IST Projects - The Quest for Excellence Towards 2020

View full text Add to dashboard Cite

show abstract

“…Two stop-lists are also used to eliminate uninteresting words and titles. After the pre-processing step, we proceed to extract the main concepts of the studied field by applying the method proposed in (Zarrad et al, 2012a;Zarrad et al, 2012b) which uses information on the document structure to extract relevant information. The taxonomic relations are discovered using syntactical method and patterns matching technique.…”

Section: General Approachmentioning

confidence: 99%

Title-based Approach to Relation Discovery from Wikipedia

Zarrad

Doggaz

Zagrouba

2013

Proceedings of the International Conference on Knowledge Engineering and Ontology Development

View full text Add to dashboard Cite

With the advent of the Web and the explosion of available textual data, the field of domain ontology engineering has gained more and more importance. The last decade, several successful tools for automatically harvesting knowledge from web data have been developed, but the extraction of taxonomic and non taxonomic ontological relationships is still far from being fully solved. This paper describes a new approach which extracts ontological relations from Wikipedia. The non-taxonomic relations extraction process is performed by analyzing the titles which appear in each document of the studied corpus. This method is based on regular expressions which appear in titles and from which we can extract not only the two arguments of the relationships but also the labels which describe the relations. The resulting set of labels is used in order to retrieve new relations by analyzing the title hierarchy in each document. Other relations can be extracted from titles and subtitles containing only one term. An enrichment step is also applied by considering each term which appears as a relation argument of the extracted links in order to discover new concepts and new relations. The experiments have been performed on French Wikipedia articles related to the medical field. The precision and recall values are encouraging and seem to validate our approach.

show abstract