dwtc-extractor:用于创建德累斯顿网络表语料库的提取代码-源码

[{"title":"（ 35 个子文件 288KB ） dwtc-extractor:用于创建德累斯顿网络表语料库的提取代码-源码","children":[{"title":"dwtc-extractor-master","children":[{"title":"bin","children":[{"title":"master <span style='color:#111;'> 127B </span>","children":null,"spread":false}],"spread":true},{"title":"pom.xml <span style='color:#111;'> 5.66KB </span>","children":null,"spread":false},{"title":"LICENSE <span style='color:#111;'> 11.09KB </span>","children":null,"spread":false},{"title":"README.markdown <span style='color:#111;'> 5.73KB </span>","children":null,"spread":false},{"title":"src","children":[{"title":"main","children":[{"title":"resources","children":[{"title":"jets3.properties <span style='color:#111;'> 139B </span>","children":null,"spread":false},{"title":"SimpleCart_P2.mdl <span style='color:#111;'> 356.71KB </span>","children":null,"spread":false},{"title":"log4j.properties <span style='color:#111;'> 294B </span>","children":null,"spread":false},{"title":"webreduce.properties <span style='color:#111;'> 856B </span>","children":null,"spread":false},{"title":"SimpleCart_P1.mdl <span style='color:#111;'> 777.73KB </span>","children":null,"spread":false},{"title":"RandomForest_P2.mdl <span style='color:#111;'> 193.46KB </span>","children":null,"spread":false},{"title":"RandomForest_P1.mdl <span style='color:#111;'> 220.32KB </span>","children":null,"spread":false}],"spread":true},{"title":"java","children":[{"title":"webreduce","children":[{"title":"extraction","children":[{"title":"ExtractionAlgorithm.java <span style='color:#111;'> 364B </span>","children":null,"spread":false},{"title":"TableExtractionModule.java <span style='color:#111;'> 1.67KB </span>","children":null,"spread":false},{"title":"mh","children":[{"title":"features","children":[{"title":"FeaturesP1.java <span style='color:#111;'> 17.37KB </span>","children":null,"spread":false},{"title":"FeaturesP2.java <span style='color:#111;'> 24.66KB </span>","children":null,"spread":false}],"spread":false},{"title":"TableClassification.java <span style='color:#111;'> 4.15KB </span>","children":null,"spread":false},{"title":"warcTools","children":[{"title":"ExtractedTable.java <span style='color:#111;'> 959B </span>","children":null,"spread":false}],"spread":false},{"title":"tools","children":[{"title":"ClassificationResult.java <span style='color:#111;'> 1.30KB </span>","children":null,"spread":false},{"title":"Tools.java <span style='color:#111;'> 3.94KB </span>","children":null,"spread":false},{"title":"TableStats.java <span style='color:#111;'> 382B </span>","children":null,"spread":false},{"title":"TableConvert.java <span style='color:#111;'> 5.44KB </span>","children":null,"spread":false},{"title":"ContentType.java <span style='color:#111;'> 331B </span>","children":null,"spread":false},{"title":"CellTools.java <span style='color:#111;'> 2.88KB </span>","children":null,"spread":false}],"spread":false},{"title":"MHExtractionAlgorithm.java <span style='color:#111;'> 6.00KB </span>","children":null,"spread":false}],"spread":true},{"title":"basic","children":[{"title":"BasicExtractionAlgorithm.java <span style='color:#111;'> 10.52KB </span>","children":null,"spread":false}],"spread":false},{"title":"StatsKeeper.java <span style='color:#111;'> 1.55KB </span>","children":null,"spread":false},{"title":"DocumentMetadata.java <span style='color:#111;'> 791B </span>","children":null,"spread":false}],"spread":true},{"title":"terms","children":[{"title":"LuceneNormalizer.java <span style='color:#111;'> 1.93KB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"org","children":[{"title":"fuberlin","children":[{"title":"wbsg","children":[{"title":"ccrdf","children":[{"title":"ProcessingNode.java <span style='color:#111;'> 4.84KB </span>","children":null,"spread":false},{"title":"StatHandler.java <span style='color:#111;'> 3.17KB </span>","children":null,"spread":false},{"title":"CSVExport.java <span style='color:#111;'> 2.40KB </span>","children":null,"spread":false},{"title":"Master.java <span style='color:#111;'> 42.97KB </span>","children":null,"spread":false},{"title":"Worker.java <span style='color:#111;'> 13.98KB </span>","children":null,"spread":false}],"spread":true}],"spread":true}],"spread":true}],"spread":true}],"spread":true}],"spread":true}],"spread":true},{"title":"2013segments <span style='color:#111;'> 8.64KB </span>","children":null,"spread":false},{"title":".gitignore <span style='color:#111;'> 53B </span>","children":null,"spread":false}],"spread":true}],"spread":true}]