China
Africa
Explore chapters and articles related to this topic
Building product models, terminologies, and object type libraries
Published in Pieter Pauwels, Kris McGlinn, Buildings and Semantics, 2023
Aaron Costin, Jeffrey W. Ouellette, Jakob Beetz
The free classification structure FreeClass provides approximately 2,800 concepts pertaining to building materials that are available in eight languages.6 This vocabulary has been used to create product catalogues of approximately 70,000 building products by 90 manufacturers in Austria that can be accessed, searched, and indexed by search engines in a uniform way. The global networking of such datasets is summarised by the notion of linked data, which has been previously discussed. Furthermore, a number of general-purpose datasets exist, such as the semantically annotated form of the Wikipedia corpus, DBPedia,7 and YAGO (Yet Another Great Ontology).8 Since the emergence of the LOD Cloud in 2007, DBpedia constitutes the main resource of linked open data on the Web containing more than 228 million entities to date. YAGO is another large knowledge base with more than 10 million entities and contains more than 120 million facts about these entities.
Multilingual and Multimodal Access
Published in Sarika Jain, Understanding Semantics-Based Decision Support, 2021
There are multiple multilingual repositories of ontologies available from which we can associate linguistic information into the ontology, or we can make our own. Following are some of those repositories:WordNet: WordNet is a lexical database and can be considered an electronic dictionary. It contains nouns, verbs, adverbs, and adjectives along with idioms and simplex words.DBpedia: DBpedia is an effort at extracting all the structured information of Wikipedia, representing it semantically in the form of RDF triples, and making it available on the semantic web.BabelNet: BabelNet is a very large, wide-coverage multilingual semantic network. It is a resource which is constructed automatically through integration of knowledge from WordNet and Wikipedia. Along with this machine learning, translations are used to enrich the repository with lexical multilingual information.YAGO: YAGO is a combination of Wikipedia, WordNet, GeoNames, and more.
An intelligent approach for mining knowledge graphs of online news
Published in International Journal of Computers and Applications, 2022
Kumar Abhishek, Vaibhav Pratihar, Shishir Kumar Shandilya, Sanju Tiwari, Vinay Kumar Ranjan, Sudhakar Tripathi
The uncountable information in the knowledge base, such as Google Knowledge Graph [1], Freebase [20], Knowledge Vault [19], Probase [21], YAGO [17], and Bing Satori [22], had been verified to be critical for various real-world assignments, such as document representation [23], question answering, and graph-based recommendation [13]. These knowledge graphs [14,24] are designed from the vast amount of noisy text data. All of the knowledge sources are open-source and available on the World Wide Web to use free of cost. These knowledge graphs are currently being used in different domains such as Artificial Intelligence, QA Systems, Chatbots, etc. and they are potential sources of knowledge that can be used to fetch related information regarding any content. The information provided by these sources is already structured and can be easily converted to other formats if required.
Geo-analytical question-answering with GIS
Published in International Journal of Digital Earth, 2021
Simon Scheider, Enkhbold Nyamsuren, Han Kruiger, Haiqi Xu
The linked data cloud7 and RDF8 have been recently proposed for KB question-answering over data cubes (Höffner, Lehmann, and Usbeck 2016), allowing answers to be retrieved over many dimensions and resolution levels. The Semantic Web can be seen as a core technique for KB QA because its particular strength lies in reasoning over taxonomic concepts (Höffner et al. 2017), and large Web data bases such as DBpedia,9 Yago10 or WordNet11 can be used for answer set generation (Bao et al. 2014). Main computational steps involve (1) the analysis of questions into phrases, (2) the mapping of phrases (including named entities) to the KB, (3) entity disambiguation, and the (4) construction and (5) firing of queries over the KB (Diefenbach et al. 2018).
Ontology-Based Modelling and Information Extracting of Physical Entities in Semantic Sensor Networks
Published in IETE Journal of Research, 2019
Mohammad Ahmadinia, Ali Movaghar, Amir Masoud Rahmani
In [20], an entity extraction system has been introduced to compute semantic relatedness. In this work, an approach has been proposed in which any text converts to a set of semantic entities to compute semantic relatedness using YAGO ontology. Also, a new algorithm for entity disambiguation has been suggested. Work [21] devises a compact or factorized representation of semantic sensor data, where repeated values are represented only once. Work [22] proposes a semantic system architecture based on service provider for data acquisition from heterogeneous sensing sources, and designs a semantic data model of service provider based on context ontology. Work [23] introduces a knowledge acquisition method that processes real-world data to automatically create and evolve topical ontologies based on rules that are automatically extracted from external sources. In this work, an extended k-means clustering method is used and a statistic model is applied to extract and link relevant concepts from the raw sensor data and represent them in the form of a topical ontology. Work [24] presents the Human-Aware Sensor Network Ontology(HASNetO) that is an alignment and integration of a sensing infrastructure ontology and a provenance ontology. In [25], a framework for ontology provisioning in vWSNs has been proposed. The framework comprises an ontology provisioning center, an ontology-enabled virtualized wireless sensor networks (vWSN) and an ontology provisioning protocol that enables the interactions between the provisioning center and the ontology-enabled vWSN.