{ "types" : { "Bookmark" : { "pluralLabel" : "Bookmarks" }, "Publication" : { "pluralLabel" : "Publications" }, "GoldStandardPublication" : { "pluralLabel" : "GoldStandardPublications" }, "GoldStandardBookmark" : { "pluralLabel" : "GoldStandardBookmarks" }, "Tag" : { "pluralLabel" : "Tags" }, "User" : { "pluralLabel" : "Users" }, "Group" : { "pluralLabel" : "Groups" }, "Sphere" : { "pluralLabel" : "Spheres" } }, "properties" : { "count" : { "valueType" : "number" }, "date" : { "valueType" : "date" }, "changeDate" : { "valueType" : "date" }, "url" : { "valueType" : "url" }, "id" : { "valueType" : "url" }, "tags" : { "valueType" : "item" }, "user" : { "valueType" : "item" } }, "items" : [ { "type" : "Bookmark", "id" : "https://puma.ub.uni-stuttgart.de/url/4c43c5da7e75b41598ea0b2cabd248b3/diglezakis", "tags" : [ "forschungsdaten","metadata","linkedData" ], "intraHash" : "4c43c5da7e75b41598ea0b2cabd248b3", "label" : "Das WikiLibrary Manifest - Wikimedia", "user" : "diglezakis", "description" : "", "date" : "2021-11-23 11:52:22", "changeDate" : "2021-11-23 10:52:22", "count" : 2, "url" : "https://www.wikimedia.de/projects/wikilibrary-manifest/" } , { "type" : "Bookmark", "id" : "https://puma.ub.uni-stuttgart.de/url/27045e3ea625fcb538419f887652591a/diglezakis", "tags" : [ "metadata","jsonLD","microdata","linkedData","statistics" ], "intraHash" : "27045e3ea625fcb538419f887652591a", "label" : "Web Data Commons Extraction Report - November 2019 Corpus", "user" : "diglezakis", "description" : "Statistics of the crawl of structured data of the Web Data Commons Project from November 2019", "date" : "2020-01-13 10:49:03", "changeDate" : "2020-01-13 09:49:03", "count" : 1, "url" : "http://webdatacommons.org/structureddata/2019-12/stats/stats.html" } , { "type" : "Bookmark", "id" : "https://puma.ub.uni-stuttgart.de/url/9c10389b04e71d00590a573ab95488aa/diglezakis", "tags" : [ "metadata","schemaOrg","linkedData","dataCite" ], "intraHash" : "9c10389b04e71d00590a573ab95488aa", "label" : "Using Schema.org for DOI Registration", "user" : "diglezakis", "description" : "", "date" : "2017-08-22 09:06:19", "changeDate" : "2017-08-22 07:06:19", "count" : 1, "url" : "https://blog.datacite.org/schema-org-register-dois/" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/24f334c0f8c03d6160eb15a0b62579558/diglezakis", "tags" : [ "metadata","linkedData","semanticWeb","integration" ], "intraHash" : "4f334c0f8c03d6160eb15a0b62579558", "interHash" : "c96c3eac1cff15103a34fbbb1025b9a0", "label" : "Large-scale Semantic Integration of Linked Data: A Survey", "user" : "diglezakis", "description" : "", "date" : "2024-06-19 15:02:54", "changeDate" : "2024-06-19 15:02:54", "count" : 2, "pub-type": "article", "journal": "ACM Comput. Surv.","publisher":"Association for Computing Machinery","address":"New York, NY, USA", "year": "2019", "url": "https://doi.org/10.1145/3345551", "author": [ "Michalis Mountantonakis","Yannis Tzitzikas" ], "authors": [ {"first" : "Michalis", "last" : "Mountantonakis"}, {"first" : "Yannis", "last" : "Tzitzikas"} ], "volume": "52","number": "5","abstract": "A large number of published datasets (or sources) that follow Linked Data principles is currently available and this number grows rapidly. However, the major target of Linked Data, i.e., linking and integration, is not easy to achieve. In general, information integration is difficult, because (a) datasets are produced, kept, or managed by different organizations using different models, schemas, or formats, (b) the same real-world entities or relationships are referred with different URIs or names and in different natural languages,(c) datasets usually contain complementary information, (d) datasets can contain data that are erroneous, out-of-date, or conflicting, (e) datasets even about the same domain may follow different conceptualizations of the domain, (f) everything can change (e.g., schemas, data) as time passes. This article surveys the work that has been done in the area of Linked Data integration, it identifies the main actors and use cases, it analyzes and factorizes the integration process according to various dimensions, and it discusses the methods that are used in each step. Emphasis is given on methods that can be used for integrating several datasets. Based on this analysis, the article concludes with directions that are worth further research.", "numpages" : "40", "articleno" : "103", "issn" : "0360-0300", "issue_date" : "September 2020", "doi" : "10.1145/3345551", "bibtexKey": "10.1145/3345551" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/24af36dbc29da579a3941c7efb2cce177/diglezakis", "tags" : [ "metadata","linkedData","quality" ], "intraHash" : "4af36dbc29da579a3941c7efb2cce177", "interHash" : "5d306174a9c00920835987cec4d4c7f3", "label" : "Quality assessment for linked data: A survey", "user" : "diglezakis", "description" : "", "date" : "2024-06-19 15:00:43", "changeDate" : "2024-06-19 15:00:43", "count" : 2, "pub-type": "article", "journal": "Semantic Web","publisher":"IOS Press", "year": "2016", "url": "", "author": [ "Amrapali Zaveri","Anisa Rula","Andrea Maurino","Ricardo Pietrobon","Jens Lehmann","Sören Auer" ], "authors": [ {"first" : "Amrapali", "last" : "Zaveri"}, {"first" : "Anisa", "last" : "Rula"}, {"first" : "Andrea", "last" : "Maurino"}, {"first" : "Ricardo", "last" : "Pietrobon"}, {"first" : "Jens", "last" : "Lehmann"}, {"first" : "Sören", "last" : "Auer"} ], "volume": "7","number": "1","pages": "63--93", "bibtexKey": "zaveri2016quality" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/282a59066ca07363abaae321592803ba4/diglezakis", "tags" : [ "metadata","linkedData","quality" ], "intraHash" : "82a59066ca07363abaae321592803ba4", "interHash" : "66a6d782062b615d9b4fa141ceb2473a", "label" : "Test-driven evaluation of linked data quality", "user" : "diglezakis", "description" : "", "date" : "2024-06-19 14:57:34", "changeDate" : "2024-06-19 14:57:34", "count" : 2, "pub-type": "inproceedings", "booktitle": "Proceedings of the 23rd International Conference on World Wide Web","series": "WWW '14","publisher":"Association for Computing Machinery","address":"New York, NY, USA", "year": "2014", "url": "https://doi.org/10.1145/2566486.2568002", "author": [ "Dimitris Kontokostas","Patrick Westphal","Sören Auer","Sebastian Hellmann","Jens Lehmann","Roland Cornelissen","Amrapali Zaveri" ], "authors": [ {"first" : "Dimitris", "last" : "Kontokostas"}, {"first" : "Patrick", "last" : "Westphal"}, {"first" : "Sören", "last" : "Auer"}, {"first" : "Sebastian", "last" : "Hellmann"}, {"first" : "Jens", "last" : "Lehmann"}, {"first" : "Roland", "last" : "Cornelissen"}, {"first" : "Amrapali", "last" : "Zaveri"} ], "pages": "747\u2013758","abstract": "Linked Open Data (LOD) comprises an unprecedented volume of structured data on the Web. However, these datasets are of varying quality ranging from extensively curated datasets to crowdsourced or extracted data of often relatively low quality. We present a methodology for test-driven quality assessment of Linked Data, which is inspired by test-driven software development. We argue that vocabularies, ontologies and knowledge bases should be accompanied by a number of test cases, which help to ensure a basic level of quality. We present a methodology for assessing the quality of linked data resources, based on a formalization of bad smells and data quality problems. Our formalization employs SPARQL query templates, which are instantiated into concrete quality test case queries. Based on an extensive survey, we compile a comprehensive library of data quality test case patterns. We perform automatic test case instantiation based on schema constraints or semi-automatically enriched schemata and allow the user to generate specific test case instantiations that are applicable to a schema or dataset. We provide an extensive evaluation of five LOD datasets, manual test case instantiation for five schemas and automatic test case instantiations for all available schemata registered with Linked Open Vocabularies (LOV). One of the main advantages of our approach is that domain specific semantics can be encoded in the data quality test cases, thus being able to discover data quality problems beyond conventional quality heuristics.", "isbn" : "9781450327442", "numpages" : "12", "location" : "Seoul, Korea", "doi" : "10.1145/2566486.2568002", "bibtexKey": "10.1145/2566486.2568002" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/23f0535ae671f41f9f7fd403414ae2472/diglezakis", "tags" : [ "metadata","linkedData","semanticWeb" ], "intraHash" : "3f0535ae671f41f9f7fd403414ae2472", "interHash" : "97ce955590fa2e076d8e24fa214aada1", "label" : "A survey on question answering systems over linked data and documents", "user" : "diglezakis", "description" : "", "date" : "2024-06-19 14:53:15", "changeDate" : "2024-06-19 14:53:48", "count" : 1, "pub-type": "article", "journal": "Journal of Intelligent Information Systems", "year": "2020", "url": "https://doi.org/10.1007/s10844-019-00584-7", "author": [ "Eleftherios Dimitrakis","Konstantinos Sgontzos","Yannis Tzitzikas" ], "authors": [ {"first" : "Eleftherios", "last" : "Dimitrakis"}, {"first" : "Konstantinos", "last" : "Sgontzos"}, {"first" : "Yannis", "last" : "Tzitzikas"} ], "volume": "55","number": "2","pages": "233--259","abstract": "Question Answering (QA) systems aim at supplying precise answers to questions, posed by users in a natural language form. They are used in a wide range of application areas, from bio-medicine to tourism. Their underlying knowledge source can be structured data (e.g. RDF graphs and SQL databases), unstructured data in the form of plain text (e.g. textual excerpts from Wikipedia), or combinations of the above. In this paper we survey the recent work that has been done in the area of stateless QA systems with emphasis on methods that have been applied in RDF and Linked Data, documents, and mixtures of these. We identify the main challenges, we categorize the existing approaches according to various aspects, we review 21 recent systems, and 23 evaluation and training datasets that are most commonly used in the literature categorized according to the type of the domain, the underlying knowledge source, the provided tasks, and the associated evaluation metrics.", "issn" : "15737675", "refid" : "Dimitrakis2020", "doi" : "10.1007/s10844-019-00584-7", "bibtexKey": "dimitrakis2020survey" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/20b3f63b768cd1cb33bafd96c1ce0c7f8/diglezakis", "tags" : [ "metadata","microdata","linkedData" ], "intraHash" : "0b3f63b768cd1cb33bafd96c1ce0c7f8", "interHash" : "1b6b05b419f93093d05f127cc884ad67", "label" : "Metadata Research: Making Digital Resources Useful Again?", "user" : "diglezakis", "description" : "", "date" : "2017-09-14 11:44:11", "changeDate" : "2017-09-14 09:44:11", "count" : 1, "pub-type": "inbook", "publisher":"World Scientific Publishing","address":"Singapore", "year": "2014", "url": "", "author": [ "Miguel-Angel Sicilia" ], "authors": [ {"first" : "Miguel-Angel", "last" : "Sicilia"} ], "editor": [ "Miguel-Angel Sicilia" ], "editors": [ {"first" : "Miguel-Angel", "last" : "Sicilia"} ], "volume": "Handbook of Metadata, Semantics and Ontologies","pages": "1-8", "isbn" : "978-981-283-629-8", "bibtexKey": "sicilia2014metadata" } ] }