├── .gitignore ├── Makefile ├── README.md ├── examples ├── extract_links.pig ├── extract_redirects.pig ├── ne-disambiguation-corpus │ └── README.md ├── ner-corpus │ ├── 01_extract_sentences_with_links.pig │ ├── 02_dbpedia_article_types.pig │ ├── 03_join_by_type_and_convert.pig │ ├── 03bis_filter_join_by_type_and_convert.pig │ └── dbpedia_to_opennlp_types.tsv └── topic-corpus │ ├── 01_count_child_topics.pig │ ├── 02_find_grounded_topics.pig │ ├── 03_find_descendants.pig │ ├── 04_find_grounded_topic_articles.pig │ ├── 05_build_grounded_ancestry.pig │ ├── 06_extract_aggregate_topic_abstracts.pig │ ├── README.md │ ├── categorize.py │ ├── download_data.sh │ └── schema.xml ├── pignlproc.properties ├── pom.xml └── src ├── main ├── java │ └── pignlproc │ │ ├── evaluation │ │ ├── AggregateTextBag.java │ │ ├── CheckAbstract.java │ │ ├── ConcatTextBag.java │ │ ├── MergeAsOpenNLPAnnotatedText.java │ │ ├── NoLoopInPath.java │ │ ├── SafeTsvText.java │ │ └── SentencesWithLink.java │ │ ├── format │ │ └── WikipediaPageInputFormat.java │ │ ├── helpers │ │ └── SpanHelper.java │ │ ├── markup │ │ ├── AnnotatingMarkupParser.java │ │ └── Annotation.java │ │ └── storage │ │ ├── AbstractNTriplesLoader.java │ │ ├── AbstractNTriplesStorer.java │ │ ├── ParsingWikipediaLoader.java │ │ ├── RawWikipediaLoader.java │ │ ├── UriStringLiteralNTriplesLoader.java │ │ ├── UriStringLiteralNTriplesStorer.java │ │ ├── UriUriNTriplesLoader.java │ │ └── UriUriNTriplesStorer.java └── resources │ └── opennlp │ └── en-sent.bin └── test ├── java └── pignlproc │ ├── evaluation │ └── TestEvalFunctions.java │ ├── format │ └── TestWikipediaParsing.java │ └── storage │ ├── TestUriStringLiteralNTriplesLoader.java │ ├── TestUriStringLiteralNTriplesStorer.java │ ├── TestUriUriNTriplesLoader.java │ ├── TestUriUriNTriplesStorer.java │ └── TestWikipediaLoader.java └── resources ├── dbpedia_3.4_instancetype_en.nt ├── dbpedia_3.4_longabstract_en.nt ├── enwiki-20090902-pages-articles-sample.xml ├── frwiki-20101103-pages-articles-sample.xml └── graph.tsv /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/.gitignore -------------------------------------------------------------------------------- /Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/Makefile -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/README.md -------------------------------------------------------------------------------- /examples/extract_links.pig: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/examples/extract_links.pig -------------------------------------------------------------------------------- /examples/extract_redirects.pig: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/examples/extract_redirects.pig -------------------------------------------------------------------------------- /examples/ne-disambiguation-corpus/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/examples/ne-disambiguation-corpus/README.md -------------------------------------------------------------------------------- /examples/ner-corpus/01_extract_sentences_with_links.pig: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/examples/ner-corpus/01_extract_sentences_with_links.pig -------------------------------------------------------------------------------- /examples/ner-corpus/02_dbpedia_article_types.pig: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/examples/ner-corpus/02_dbpedia_article_types.pig -------------------------------------------------------------------------------- /examples/ner-corpus/03_join_by_type_and_convert.pig: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/examples/ner-corpus/03_join_by_type_and_convert.pig -------------------------------------------------------------------------------- /examples/ner-corpus/03bis_filter_join_by_type_and_convert.pig: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/examples/ner-corpus/03bis_filter_join_by_type_and_convert.pig -------------------------------------------------------------------------------- /examples/ner-corpus/dbpedia_to_opennlp_types.tsv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/examples/ner-corpus/dbpedia_to_opennlp_types.tsv -------------------------------------------------------------------------------- /examples/topic-corpus/01_count_child_topics.pig: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/examples/topic-corpus/01_count_child_topics.pig -------------------------------------------------------------------------------- /examples/topic-corpus/02_find_grounded_topics.pig: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/examples/topic-corpus/02_find_grounded_topics.pig -------------------------------------------------------------------------------- /examples/topic-corpus/03_find_descendants.pig: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/examples/topic-corpus/03_find_descendants.pig -------------------------------------------------------------------------------- /examples/topic-corpus/04_find_grounded_topic_articles.pig: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/examples/topic-corpus/04_find_grounded_topic_articles.pig -------------------------------------------------------------------------------- /examples/topic-corpus/05_build_grounded_ancestry.pig: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/examples/topic-corpus/05_build_grounded_ancestry.pig -------------------------------------------------------------------------------- /examples/topic-corpus/06_extract_aggregate_topic_abstracts.pig: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/examples/topic-corpus/06_extract_aggregate_topic_abstracts.pig -------------------------------------------------------------------------------- /examples/topic-corpus/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/examples/topic-corpus/README.md -------------------------------------------------------------------------------- /examples/topic-corpus/categorize.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/examples/topic-corpus/categorize.py -------------------------------------------------------------------------------- /examples/topic-corpus/download_data.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/examples/topic-corpus/download_data.sh -------------------------------------------------------------------------------- /examples/topic-corpus/schema.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/examples/topic-corpus/schema.xml -------------------------------------------------------------------------------- /pignlproc.properties: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/pignlproc.properties -------------------------------------------------------------------------------- /pom.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/pom.xml -------------------------------------------------------------------------------- /src/main/java/pignlproc/evaluation/AggregateTextBag.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/src/main/java/pignlproc/evaluation/AggregateTextBag.java -------------------------------------------------------------------------------- /src/main/java/pignlproc/evaluation/CheckAbstract.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/src/main/java/pignlproc/evaluation/CheckAbstract.java -------------------------------------------------------------------------------- /src/main/java/pignlproc/evaluation/ConcatTextBag.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/src/main/java/pignlproc/evaluation/ConcatTextBag.java -------------------------------------------------------------------------------- /src/main/java/pignlproc/evaluation/MergeAsOpenNLPAnnotatedText.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/src/main/java/pignlproc/evaluation/MergeAsOpenNLPAnnotatedText.java -------------------------------------------------------------------------------- /src/main/java/pignlproc/evaluation/NoLoopInPath.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/src/main/java/pignlproc/evaluation/NoLoopInPath.java -------------------------------------------------------------------------------- /src/main/java/pignlproc/evaluation/SafeTsvText.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/src/main/java/pignlproc/evaluation/SafeTsvText.java -------------------------------------------------------------------------------- /src/main/java/pignlproc/evaluation/SentencesWithLink.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/src/main/java/pignlproc/evaluation/SentencesWithLink.java -------------------------------------------------------------------------------- /src/main/java/pignlproc/format/WikipediaPageInputFormat.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/src/main/java/pignlproc/format/WikipediaPageInputFormat.java -------------------------------------------------------------------------------- /src/main/java/pignlproc/helpers/SpanHelper.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/src/main/java/pignlproc/helpers/SpanHelper.java -------------------------------------------------------------------------------- /src/main/java/pignlproc/markup/AnnotatingMarkupParser.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/src/main/java/pignlproc/markup/AnnotatingMarkupParser.java -------------------------------------------------------------------------------- /src/main/java/pignlproc/markup/Annotation.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/src/main/java/pignlproc/markup/Annotation.java -------------------------------------------------------------------------------- /src/main/java/pignlproc/storage/AbstractNTriplesLoader.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/src/main/java/pignlproc/storage/AbstractNTriplesLoader.java -------------------------------------------------------------------------------- /src/main/java/pignlproc/storage/AbstractNTriplesStorer.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/src/main/java/pignlproc/storage/AbstractNTriplesStorer.java -------------------------------------------------------------------------------- /src/main/java/pignlproc/storage/ParsingWikipediaLoader.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/src/main/java/pignlproc/storage/ParsingWikipediaLoader.java -------------------------------------------------------------------------------- /src/main/java/pignlproc/storage/RawWikipediaLoader.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/src/main/java/pignlproc/storage/RawWikipediaLoader.java -------------------------------------------------------------------------------- /src/main/java/pignlproc/storage/UriStringLiteralNTriplesLoader.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/src/main/java/pignlproc/storage/UriStringLiteralNTriplesLoader.java -------------------------------------------------------------------------------- /src/main/java/pignlproc/storage/UriStringLiteralNTriplesStorer.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/src/main/java/pignlproc/storage/UriStringLiteralNTriplesStorer.java -------------------------------------------------------------------------------- /src/main/java/pignlproc/storage/UriUriNTriplesLoader.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/src/main/java/pignlproc/storage/UriUriNTriplesLoader.java -------------------------------------------------------------------------------- /src/main/java/pignlproc/storage/UriUriNTriplesStorer.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/src/main/java/pignlproc/storage/UriUriNTriplesStorer.java -------------------------------------------------------------------------------- /src/main/resources/opennlp/en-sent.bin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/src/main/resources/opennlp/en-sent.bin -------------------------------------------------------------------------------- /src/test/java/pignlproc/evaluation/TestEvalFunctions.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/src/test/java/pignlproc/evaluation/TestEvalFunctions.java -------------------------------------------------------------------------------- /src/test/java/pignlproc/format/TestWikipediaParsing.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/src/test/java/pignlproc/format/TestWikipediaParsing.java -------------------------------------------------------------------------------- /src/test/java/pignlproc/storage/TestUriStringLiteralNTriplesLoader.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/src/test/java/pignlproc/storage/TestUriStringLiteralNTriplesLoader.java -------------------------------------------------------------------------------- /src/test/java/pignlproc/storage/TestUriStringLiteralNTriplesStorer.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/src/test/java/pignlproc/storage/TestUriStringLiteralNTriplesStorer.java -------------------------------------------------------------------------------- /src/test/java/pignlproc/storage/TestUriUriNTriplesLoader.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/src/test/java/pignlproc/storage/TestUriUriNTriplesLoader.java -------------------------------------------------------------------------------- /src/test/java/pignlproc/storage/TestUriUriNTriplesStorer.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/src/test/java/pignlproc/storage/TestUriUriNTriplesStorer.java -------------------------------------------------------------------------------- /src/test/java/pignlproc/storage/TestWikipediaLoader.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/src/test/java/pignlproc/storage/TestWikipediaLoader.java -------------------------------------------------------------------------------- /src/test/resources/dbpedia_3.4_instancetype_en.nt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/src/test/resources/dbpedia_3.4_instancetype_en.nt -------------------------------------------------------------------------------- /src/test/resources/dbpedia_3.4_longabstract_en.nt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/src/test/resources/dbpedia_3.4_longabstract_en.nt -------------------------------------------------------------------------------- /src/test/resources/enwiki-20090902-pages-articles-sample.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/src/test/resources/enwiki-20090902-pages-articles-sample.xml -------------------------------------------------------------------------------- /src/test/resources/frwiki-20101103-pages-articles-sample.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/src/test/resources/frwiki-20101103-pages-articles-sample.xml -------------------------------------------------------------------------------- /src/test/resources/graph.tsv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ogrisel/pignlproc/HEAD/src/test/resources/graph.tsv --------------------------------------------------------------------------------