Merge branch 'master' of https://git.informatik.uni-leipzig.de/dbpedia-assoc/marvin-config

.gitignore

-databus-maven-plugin/
+databus-poms/dbpedia/*/*/*/
 extraction-framework/
 wikidumps/
 logs/

databus-poms/dbpedia/generic/anchor-text/anchor-text.md

+# Anchor text of Wikilinks 
+Human readable text (anchor text) of Wikilinks to refer to other Wikipedia articles
+

databus-poms/dbpedia/generic/anchor-text/pom.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project xmlns="http://maven.apache.org/POM/4.0.0"
+         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
+    <parent>
+        <groupId>generic</groupId>
+        <artifactId>group-metadata</artifactId>
+        <version>2018.08.15</version>
+    </parent>
+    <modelVersion>4.0.0</modelVersion>
+    <groupId>generic</groupId>
+    <artifactId>anchor-text</artifactId>
+    <packaging>jar</packaging>
+
+    <properties>
+        <databus.codeReference>https://github.com/dbpedia/extraction-framework/blob/master/core/src/org/dbpedia/extraction/mappings/AnchorTextExtractor.scala</databus.codeReference>
+    </properties>
+
+</project>

databus-poms/dbpedia/generic/article-templates/article-templates.md

+# Used Wikipedia Templates per Article 
+Dataset contains identifiers for used templates per Wikipedia article using the wikiPageUsesTemplate property
+
+Template identifiers (objects) use prefix `http://dbpedia.org/resource/Template:` followed by template name. 

databus-poms/dbpedia/generic/article-templates/pom.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project xmlns="http://maven.apache.org/POM/4.0.0"
+         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
+    <parent>
+        <groupId>generic</groupId>
+        <artifactId>group-metadata</artifactId>
+        <version>2020.02.01</version>
+    </parent>
+    <modelVersion>4.0.0</modelVersion>
+    <groupId>generic</groupId>
+    <artifactId>article-templates</artifactId>
+    <packaging>jar</packaging>
+
+    <properties>
+        <databus.codeReference>https://github.com/dbpedia/extraction-framework/blob/master/core/src/org/dbpedia/extraction/mappings/ArticleTemplatesExtractor.scala</databus.codeReference>
+    </properties>
+
+</project>

databus-poms/dbpedia/generic/categories/categories.md

+# Wikipedia Article Categories and categories metadata
+Contains the Wikipedia categories per Article and category metadata (hierarchy and labels)
+
+The dataset is split into 3 different types of files. The `_articles` files contain the  Wikipedia categories assigned per article connected via `dct:subject`. The `skos` files partially describe the Wikipedia Category system modelled with the [SKOS vocabulary]. For each category `skos:prefLabel`, parent categories (using `skos:broader`), and `skos:related` categories are extracted. The `labels` categories contain the `rdfs:label` of the category resources. 
+

databus-poms/dbpedia/generic/categories/pom.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project xmlns="http://maven.apache.org/POM/4.0.0"
+         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
+    <parent>
+        <groupId>generic</groupId>
+        <artifactId>group-metadata</artifactId>
+        <version>2020.02.01</version>
+    </parent>
+    <modelVersion>4.0.0</modelVersion>
+    <groupId>generic</groupId>
+    <artifactId>categories</artifactId>
+    <packaging>jar</packaging>
+
+
+</project>

databus-poms/dbpedia/generic/citations/citations.md

+# Citations and References
+Contains citations from articles and bibliographic information of the references
+
+The `_links` files contain the citations of one article by linking the citation URL via `isCitedBy` property. The `_data` files contain bibliographic metadata (e.g. format, title, author, website, accessdate, etc. if available) for the citations.   

databus-poms/dbpedia/generic/citations/pom.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project xmlns="http://maven.apache.org/POM/4.0.0"
+         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
+    <parent>
+        <groupId>generic</groupId>
+        <artifactId>group-metadata</artifactId>
+        <version>2020.02.01</version>
+    </parent>
+    <modelVersion>4.0.0</modelVersion>
+    <groupId>generic</groupId>
+    <artifactId>citations</artifactId>
+    <packaging>jar</packaging>
+
+    <properties>
+        <databus.codeReference>https://github.com/dbpedia/extraction-framework/blob/master/core/src/org/dbpedia/extraction/mappings/CitationExtractor.scala</databus.codeReference>
+    </properties>
+</project>

databus-poms/dbpedia/generic/commons-sameas-links/commons-sameas-links.md

+# Commons sameAs Links 
+Links non-commons DBpedia resources to their DBpedia Commons
+
+Extracts `owl:sameAs` to Commons Resources based on `{{Commons}}` template.
+ 
\ No newline at end of file

databus-poms/dbpedia/generic/commons-sameas-links/pom.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project xmlns="http://maven.apache.org/POM/4.0.0"
+         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
+    <parent>
+        <groupId>generic</groupId>
+        <artifactId>group-metadata</artifactId>
+        <version>2020.02.01</version>
+    </parent>
+    <modelVersion>4.0.0</modelVersion>
+    <groupId>generic</groupId>
+    <artifactId>commons-sameas-links</artifactId>
+    <packaging>jar</packaging>
+
+    <properties>
+        <databus.codeReference>https://github.com/dbpedia/extraction-framework/blob/master/core/src/org/dbpedia/extraction/mappings/CommonsResourceExtractor.scala</databus.codeReference>
+    </properties>
+
+</project>

databus-poms/dbpedia/generic/disambiguations/disambiguations.md

+# Entity Disambiguation Links
+Disambiguation Links extracted from Wikipedia disambiguation pages
+
+The links are extracted from [Wikipedia](http://en.wikipedia.org/wiki/Wikipedia:Disambiguation disambiguation) pages. Since Wikipedia has no syntax to distinguish disambiguation links from ordinary links, heuristics are used.
+
+ 
+

databus-poms/dbpedia/generic/disambiguations/pom.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project xmlns="http://maven.apache.org/POM/4.0.0"
+         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
+   <parent>
+        <groupId>generic</groupId>
+        <artifactId>group-metadata</artifactId>
+        <version>2020.02.01</version>
+    </parent>
+    <modelVersion>4.0.0</modelVersion>
+    <groupId>generic</groupId>
+    <artifactId>disambiguations</artifactId>
+    <packaging>jar</packaging>
+
+    <properties>
+        <databus.codeReference>https://github.com/dbpedia/extraction-framework/blob/master/core/src/org/dbpedia/extraction/mappings/DisambiguationExtractor.scala</databus.codeReference>
+    </properties>
+
+</project>

databus-poms/dbpedia/generic/external-links/external-links.md

+# External links 
+Links extracted from Wikitext to external web pages
+
+Every link spotted in the Wikitext of a resource will be added via  `wikiPageExternalLink` property.
\ No newline at end of file

databus-poms/dbpedia/generic/external-links/pom.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project xmlns="http://maven.apache.org/POM/4.0.0"
+         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
+    <parent>
+        <groupId>generic</groupId>
+        <artifactId>group-metadata</artifactId>
+        <version>2020.02.01</version>
+    </parent>
+    <modelVersion>4.0.0</modelVersion>
+    <groupId>generic</groupId>
+    <artifactId>external-links</artifactId>
+    <packaging>jar</packaging>
+
+    <properties>
+        <databus.codeReference>https://github.com/dbpedia/extraction-framework/blob/master/core/src/org/dbpedia/extraction/mappings/ExternalLinksExtractor.scala</databus.codeReference>
+    </properties>
+
+
+</project>

databus-poms/dbpedia/generic/geo-coordinates/geo-coordinates.md

+# geo-coordinates dataset
+help needed

databus-poms/dbpedia/generic/geo-coordinates/pom.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project xmlns="http://maven.apache.org/POM/4.0.0"
+         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
+    <parent>
+        <groupId>generic</groupId>
+        <artifactId>group-metadata</artifactId>
+        <version>2020.02.01</version>
+    </parent>
+    <modelVersion>4.0.0</modelVersion>
+    <groupId>generic</groupId>
+    <artifactId>geo-coordinates</artifactId>
+    <packaging>jar</packaging>
+
+</project>

databus-poms/dbpedia/generic/homepages/homepages.md

+# homepages dataset
+help needed

databus-poms/dbpedia/generic/homepages/pom.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project xmlns="http://maven.apache.org/POM/4.0.0"
+         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
+    <parent>
+        <groupId>generic</groupId>
+        <artifactId>group-metadata</artifactId>
+        <version>2020.02.01</version>
+    </parent>
+    <modelVersion>4.0.0</modelVersion>
+    <groupId>generic</groupId>
+    <artifactId>homepages</artifactId>
+    <packaging>jar</packaging>
+ 
+
+</project>

databus-poms/dbpedia/generic/infobox-properties/infobox-properties.md

+# Extracted facts from Wikipedia Infoboxes
+Data from Wikipedia's infoboxes, as is with some smart automatic (generic) parsing. This dataset has the best fact coverage, but has less consistency than the cleaned mapping infobox dataset.