├── .travis.yml ├── LICENSE.txt ├── README.md ├── alto_tools ├── AltoToBio │ ├── pom.xml │ └── src │ │ └── main │ │ └── java │ │ └── nl │ │ └── kbresearch │ │ └── europeana_newspapers │ │ └── AltoToBio │ │ ├── AltoToBio.java │ │ └── EntityReference.java ├── alto_to_text.py └── parse_stanford_vanilla.py ├── go.sh ├── pom.xml ├── src ├── .gitignore ├── main │ ├── .gitignore │ ├── java │ │ └── nl │ │ │ └── kbresearch │ │ │ └── europeana_newspapers │ │ │ └── NerAnnotator │ │ │ ├── App.java │ │ │ ├── NERClassifiers.java │ │ │ ├── TextElementsExtractor.java │ │ │ ├── WebApp.java │ │ │ ├── alto │ │ │ ├── AltoProcessor.java │ │ │ ├── AltoStringID.java │ │ │ ├── ContinuationAltoStringID.java │ │ │ ├── HyphenatedLineBreak.java │ │ │ ├── OriginalContent.java │ │ │ └── TxtProcessor.java │ │ │ ├── container │ │ │ ├── AltoLocalProcessor.java │ │ │ ├── ContainerContext.java │ │ │ ├── ContainerHandleThread.java │ │ │ ├── ContainerProcessor.java │ │ │ ├── DIDLProcessor.java │ │ │ ├── HtmlProcessor.java │ │ │ ├── MetsProcessor.java │ │ │ └── TextProcessor.java │ │ │ ├── http │ │ │ └── NERhttp.java │ │ │ └── output │ │ │ ├── Alto2_1ResultHandler.java │ │ │ ├── Alto3ResultHandler.java │ │ │ ├── AnnotatedAltoResultHandler.java │ │ │ ├── BioResultHandler.java │ │ │ ├── CsvResultHandler.java │ │ │ ├── DbResultHandler.java │ │ │ ├── HtmlResultHandler.java │ │ │ ├── HttpResultHandler.java │ │ │ ├── LogResultHandler.java │ │ │ ├── ResultHandler.java │ │ │ └── ResultHandlerFactory.java │ ├── resources │ │ ├── .gitignore │ │ ├── config.ini │ │ ├── eunews_dutch.crf.gz │ │ └── eunews_german.crf.gz │ └── webapp │ │ └── WEB-INF │ │ └── web.xml └── test │ ├── .gitignore │ └── java │ ├── .gitignore │ └── nl │ └── kbresearch │ └── europeana_newspapers │ └── NerAnnotator │ └── AppTest.java └── test-files ├── Dutch_AltoInline_OutputExample.xml ├── German_AltoInline_OutputExample.xml ├── README.md ├── austen_dutch.prop ├── austen_german.prop ├── dutch.bio ├── dutch_alto.xml ├── dutch_alto1.xml ├── dutch_gazette_example.list ├── german.bio ├── german_alto.xml ├── german_alto1.xml ├── test_commandLine_ner.sh └── test_webInterface_ner.sh /.travis.yml: -------------------------------------------------------------------------------- 1 | language: java 2 | notifications: 3 | email: false -------------------------------------------------------------------------------- /LICENSE.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/LICENSE.txt -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/README.md -------------------------------------------------------------------------------- /alto_tools/AltoToBio/pom.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/alto_tools/AltoToBio/pom.xml -------------------------------------------------------------------------------- /alto_tools/AltoToBio/src/main/java/nl/kbresearch/europeana_newspapers/AltoToBio/AltoToBio.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/alto_tools/AltoToBio/src/main/java/nl/kbresearch/europeana_newspapers/AltoToBio/AltoToBio.java -------------------------------------------------------------------------------- /alto_tools/AltoToBio/src/main/java/nl/kbresearch/europeana_newspapers/AltoToBio/EntityReference.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/alto_tools/AltoToBio/src/main/java/nl/kbresearch/europeana_newspapers/AltoToBio/EntityReference.java -------------------------------------------------------------------------------- /alto_tools/alto_to_text.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/alto_tools/alto_to_text.py -------------------------------------------------------------------------------- /alto_tools/parse_stanford_vanilla.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/alto_tools/parse_stanford_vanilla.py -------------------------------------------------------------------------------- /go.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/go.sh -------------------------------------------------------------------------------- /pom.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/pom.xml -------------------------------------------------------------------------------- /src/.gitignore: -------------------------------------------------------------------------------- 1 | /.DS_Store 2 | -------------------------------------------------------------------------------- /src/main/.gitignore: -------------------------------------------------------------------------------- 1 | /.DS_Store 2 | -------------------------------------------------------------------------------- /src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/App.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/App.java -------------------------------------------------------------------------------- /src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/NERClassifiers.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/NERClassifiers.java -------------------------------------------------------------------------------- /src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/TextElementsExtractor.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/TextElementsExtractor.java -------------------------------------------------------------------------------- /src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/WebApp.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/WebApp.java -------------------------------------------------------------------------------- /src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/alto/AltoProcessor.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/alto/AltoProcessor.java -------------------------------------------------------------------------------- /src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/alto/AltoStringID.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/alto/AltoStringID.java -------------------------------------------------------------------------------- /src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/alto/ContinuationAltoStringID.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/alto/ContinuationAltoStringID.java -------------------------------------------------------------------------------- /src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/alto/HyphenatedLineBreak.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/alto/HyphenatedLineBreak.java -------------------------------------------------------------------------------- /src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/alto/OriginalContent.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/alto/OriginalContent.java -------------------------------------------------------------------------------- /src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/alto/TxtProcessor.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/alto/TxtProcessor.java -------------------------------------------------------------------------------- /src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/container/AltoLocalProcessor.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/container/AltoLocalProcessor.java -------------------------------------------------------------------------------- /src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/container/ContainerContext.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/container/ContainerContext.java -------------------------------------------------------------------------------- /src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/container/ContainerHandleThread.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/container/ContainerHandleThread.java -------------------------------------------------------------------------------- /src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/container/ContainerProcessor.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/container/ContainerProcessor.java -------------------------------------------------------------------------------- /src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/container/DIDLProcessor.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/container/DIDLProcessor.java -------------------------------------------------------------------------------- /src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/container/HtmlProcessor.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/container/HtmlProcessor.java -------------------------------------------------------------------------------- /src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/container/MetsProcessor.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/container/MetsProcessor.java -------------------------------------------------------------------------------- /src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/container/TextProcessor.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/container/TextProcessor.java -------------------------------------------------------------------------------- /src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/http/NERhttp.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/http/NERhttp.java -------------------------------------------------------------------------------- /src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/output/Alto2_1ResultHandler.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/output/Alto2_1ResultHandler.java -------------------------------------------------------------------------------- /src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/output/Alto3ResultHandler.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/output/Alto3ResultHandler.java -------------------------------------------------------------------------------- /src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/output/AnnotatedAltoResultHandler.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/output/AnnotatedAltoResultHandler.java -------------------------------------------------------------------------------- /src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/output/BioResultHandler.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/output/BioResultHandler.java -------------------------------------------------------------------------------- /src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/output/CsvResultHandler.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/output/CsvResultHandler.java -------------------------------------------------------------------------------- /src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/output/DbResultHandler.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/output/DbResultHandler.java -------------------------------------------------------------------------------- /src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/output/HtmlResultHandler.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/output/HtmlResultHandler.java -------------------------------------------------------------------------------- /src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/output/HttpResultHandler.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/output/HttpResultHandler.java -------------------------------------------------------------------------------- /src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/output/LogResultHandler.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/output/LogResultHandler.java -------------------------------------------------------------------------------- /src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/output/ResultHandler.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/output/ResultHandler.java -------------------------------------------------------------------------------- /src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/output/ResultHandlerFactory.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/src/main/java/nl/kbresearch/europeana_newspapers/NerAnnotator/output/ResultHandlerFactory.java -------------------------------------------------------------------------------- /src/main/resources/.gitignore: -------------------------------------------------------------------------------- 1 | /.DS_Store 2 | -------------------------------------------------------------------------------- /src/main/resources/config.ini: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/src/main/resources/config.ini -------------------------------------------------------------------------------- /src/main/resources/eunews_dutch.crf.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/src/main/resources/eunews_dutch.crf.gz -------------------------------------------------------------------------------- /src/main/resources/eunews_german.crf.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/src/main/resources/eunews_german.crf.gz -------------------------------------------------------------------------------- /src/main/webapp/WEB-INF/web.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/src/main/webapp/WEB-INF/web.xml -------------------------------------------------------------------------------- /src/test/.gitignore: -------------------------------------------------------------------------------- 1 | /.DS_Store 2 | -------------------------------------------------------------------------------- /src/test/java/.gitignore: -------------------------------------------------------------------------------- 1 | /.DS_Store 2 | -------------------------------------------------------------------------------- /src/test/java/nl/kbresearch/europeana_newspapers/NerAnnotator/AppTest.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/src/test/java/nl/kbresearch/europeana_newspapers/NerAnnotator/AppTest.java -------------------------------------------------------------------------------- /test-files/Dutch_AltoInline_OutputExample.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/test-files/Dutch_AltoInline_OutputExample.xml -------------------------------------------------------------------------------- /test-files/German_AltoInline_OutputExample.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/test-files/German_AltoInline_OutputExample.xml -------------------------------------------------------------------------------- /test-files/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/test-files/README.md -------------------------------------------------------------------------------- /test-files/austen_dutch.prop: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/test-files/austen_dutch.prop -------------------------------------------------------------------------------- /test-files/austen_german.prop: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/test-files/austen_german.prop -------------------------------------------------------------------------------- /test-files/dutch.bio: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/test-files/dutch.bio -------------------------------------------------------------------------------- /test-files/dutch_alto.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/test-files/dutch_alto.xml -------------------------------------------------------------------------------- /test-files/dutch_alto1.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/test-files/dutch_alto1.xml -------------------------------------------------------------------------------- /test-files/dutch_gazette_example.list: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/test-files/dutch_gazette_example.list -------------------------------------------------------------------------------- /test-files/german.bio: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/test-files/german.bio -------------------------------------------------------------------------------- /test-files/german_alto.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/test-files/german_alto.xml -------------------------------------------------------------------------------- /test-files/german_alto1.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/test-files/german_alto1.xml -------------------------------------------------------------------------------- /test-files/test_commandLine_ner.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/test-files/test_commandLine_ner.sh -------------------------------------------------------------------------------- /test-files/test_webInterface_ner.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/KBNLresearch/europeananp-ner/HEAD/test-files/test_webInterface_ner.sh --------------------------------------------------------------------------------