Menu
▾
▴
[DL-Learner SVN] SF.net SVN: dl-learner:[4132] trunk/components-core/src
|
From: <dfl...@us...> - 2013-10-29 13:23:48
|
Revision: 4132
http://sourceforge.net/p/dl-learner/code/4132
Author: dfleischhacker
Date: 2013-10-29 13:23:45 +0000 (Tue, 29 Oct 2013)
Log Message:
-----------
Bible test case activated
Modified Paths:
--------------
trunk/components-core/src/main/java/org/dllearner/algorithms/isle/index/SimpleEntityCandidatesTrie.java
trunk/components-core/src/main/java/org/dllearner/algorithms/isle/index/syntactic/OWLOntologyLuceneSyntacticIndexCreator.java
trunk/components-core/src/test/java/org/dllearner/algorithms/isle/ISLETestCorpus.java
Modified: trunk/components-core/src/main/java/org/dllearner/algorithms/isle/index/SimpleEntityCandidatesTrie.java
===================================================================
--- trunk/components-core/src/main/java/org/dllearner/algorithms/isle/index/SimpleEntityCandidatesTrie.java 2013-10-29 08:55:58 UTC (rev 4131)
+++ trunk/components-core/src/main/java/org/dllearner/algorithms/isle/index/SimpleEntityCandidatesTrie.java 2013-10-29 13:23:45 UTC (rev 4132)
@@ -55,7 +55,7 @@
addSubsequencesWordNet(entity, text);
for (String alternativeText : nameGenerator.getAlternativeText(text)) {
- addEntry(alternativeText, entity, text);
+ addEntry(alternativeText.toLowerCase(), entity, text);
}
}
}
@@ -101,36 +101,46 @@
}
// generate subsequences starting at the given start index of the given size
- Set<String> allPossibleSubsequences = getAllPossibleSubsequences(wordnetTokens);
+ Set<String[]> allPossibleSubsequences = getAllPossibleSubsequences(tokens, wordnetTokens);
- for (String s : allPossibleSubsequences) {
- addEntry(s, entity);
+ for (String[] s : allPossibleSubsequences) {
+ addEntry(s[0], entity, s[1]);
}
}
}
- private static Set<String> getAllPossibleSubsequences(List<String>[] wordnetTokens) {
- ArrayList<String> res = new ArrayList<String>();
+ private static Set<String[]> getAllPossibleSubsequences(String[] originalTokens, List<String>[] wordnetTokens) {
+ ArrayList<String[]> res = new ArrayList<String[]>();
for (int size = 1; size < wordnetTokens.length + 1; size++) {
for (int start = 0; start < wordnetTokens.length - size + 1; start++) {
- getPossibleSubsequencesRec(res, new ArrayList<String>(), wordnetTokens, 0, size);
+ getPossibleSubsequencesRec(originalTokens, res, new ArrayList<String>(), new ArrayList<String>(),
+ wordnetTokens, 0, size);
}
}
- return new HashSet<String>(res);
+ return new HashSet<String[]>(res);
}
- private static void getPossibleSubsequencesRec(List<String> allSubsequences, List<String> currentSubsequence, List<String>[] wordnetTokens,
- int curStart, int maxLength) {
+
+ private static void getPossibleSubsequencesRec(String[] originalTokens, List<String[]> allSubsequences,
+ List<String> currentSubsequence,
+ List<String> currentOriginalSubsequence,
+ List<String>[] wordnetTokens,
+ int curStart, int maxLength) {
+
if (currentSubsequence.size() == maxLength) {
- allSubsequences.add(StringUtils.join(currentSubsequence, " "));
+ allSubsequences.add(new String[]{StringUtils.join(currentSubsequence, " ").toLowerCase(), StringUtils
+ .join(currentOriginalSubsequence, " ").toLowerCase()});
return;
}
for (String w : wordnetTokens[curStart]) {
ArrayList<String> tmpSequence = new ArrayList<String>(currentSubsequence);
+ ArrayList<String> tmpOriginalSequence = new ArrayList<String>(currentOriginalSubsequence);
tmpSequence.add(w);
- getPossibleSubsequencesRec(allSubsequences, tmpSequence, wordnetTokens, curStart + 1, maxLength);
+ tmpOriginalSequence.add(originalTokens[curStart]);
+ getPossibleSubsequencesRec(originalTokens, allSubsequences, tmpSequence, tmpOriginalSequence, wordnetTokens,
+ curStart + 1, maxLength);
}
}
@@ -183,7 +193,7 @@
List<String> termsList = new ArrayList<String>(trieMap.keySet());
Collections.sort(termsList);
for (String key : termsList) {
- output += key + ":\n";
+ output += key + " (" + trieMap.get(key).getFullToken() + ") :\n";
for (Entity candidate: trieMap.get(key).getEntitySet()) {
output += "\t"+candidate+"\n";
}
@@ -207,10 +217,10 @@
}
// generate subsequences starting at the given start index of the given size
- Set<String> allPossibleSubsequences = getAllPossibleSubsequences(wordnetTokens);
+ Set<String[]> allPossibleSubsequences = getAllPossibleSubsequences(tokens, wordnetTokens);
- for (String s : allPossibleSubsequences) {
- System.out.println(s);
+ for (String[] s : allPossibleSubsequences) {
+ System.out.println(String.format("%s - %s", s[0], s[1]));
}
}
Modified: trunk/components-core/src/main/java/org/dllearner/algorithms/isle/index/syntactic/OWLOntologyLuceneSyntacticIndexCreator.java
===================================================================
--- trunk/components-core/src/main/java/org/dllearner/algorithms/isle/index/syntactic/OWLOntologyLuceneSyntacticIndexCreator.java 2013-10-29 08:55:58 UTC (rev 4131)
+++ trunk/components-core/src/main/java/org/dllearner/algorithms/isle/index/syntactic/OWLOntologyLuceneSyntacticIndexCreator.java 2013-10-29 13:23:45 UTC (rev 4132)
@@ -42,7 +42,7 @@
this.ontology = ontology;
this.annotationProperty = annotationProperty;
this.searchField = searchField;
-
+
schemaEntities = new HashSet<OWLEntity>();
schemaEntities.addAll(ontology.getClassesInSignature());
schemaEntities.addAll(ontology.getObjectPropertiesInSignature());
Modified: trunk/components-core/src/test/java/org/dllearner/algorithms/isle/ISLETestCorpus.java
===================================================================
--- trunk/components-core/src/test/java/org/dllearner/algorithms/isle/ISLETestCorpus.java 2013-10-29 08:55:58 UTC (rev 4131)
+++ trunk/components-core/src/test/java/org/dllearner/algorithms/isle/ISLETestCorpus.java 2013-10-29 13:23:45 UTC (rev 4132)
@@ -6,14 +6,12 @@
import com.google.common.base.Charsets;
import com.google.common.base.Joiner;
import com.google.common.io.Files;
-import com.hp.hpl.jena.vocabulary.RDFS;
-
import org.dllearner.algorithms.celoe.CELOE;
import org.dllearner.algorithms.isle.index.*;
import org.dllearner.algorithms.isle.index.semantic.SemanticIndex;
import org.dllearner.algorithms.isle.index.semantic.simple.SimpleSemanticIndex;
-import org.dllearner.algorithms.isle.index.syntactic.OWLOntologyLuceneSyntacticIndexCreator;
import org.dllearner.algorithms.isle.index.syntactic.SyntacticIndex;
+import org.dllearner.algorithms.isle.index.syntactic.TextDocumentSyntacticIndexCreator;
import org.dllearner.algorithms.isle.metrics.PMIRelevanceMetric;
import org.dllearner.algorithms.isle.metrics.RelevanceMetric;
import org.dllearner.algorithms.isle.metrics.RelevanceUtils;
@@ -32,17 +30,12 @@
import org.junit.Before;
import org.junit.Test;
import org.semanticweb.owlapi.apibinding.OWLManager;
-import org.semanticweb.owlapi.model.IRI;
-import org.semanticweb.owlapi.model.OWLDataFactory;
-import org.semanticweb.owlapi.model.OWLEntity;
-import org.semanticweb.owlapi.model.OWLOntology;
-import org.semanticweb.owlapi.model.OWLOntologyManager;
-import org.semanticweb.owlapi.vocab.OWLRDFVocabulary;
-
+import org.semanticweb.owlapi.model.*;
import uk.ac.manchester.cs.owl.owlapi.OWLDataFactoryImpl;
import java.io.File;
import java.io.IOException;
+import java.net.URL;
import java.text.DecimalFormat;
import java.util.HashSet;
import java.util.Map;
@@ -80,10 +73,10 @@
manager = OWLManager.createOWLOntologyManager();
ontology = manager.loadOntologyFromOntologyDocument(new File(testFolder + "ontology.owl"));
textRetriever = new RDFSLabelEntityTextRetriever(ontology);
- syntacticIndex = new OWLOntologyLuceneSyntacticIndexCreator(ontology, df.getRDFSLabel(), searchField).buildIndex();
-
-
- }
+ RemoteDataProvider chapterIndexProvider = new RemoteDataProvider(
+ new URL("http://gold.linkeddata.org/data/bible/chapter_index.zip"));
+ syntacticIndex = TextDocumentSyntacticIndexCreator.loadIndex(chapterIndexProvider.getLocalDirectory());
+ }
private Set<TextDocument> createDocuments(){
Set<TextDocument> documents = new HashSet<TextDocument>();
@@ -100,10 +93,27 @@
}
return documents;
}
-
-
- /**
+ private Set<TextDocument> createBibleDocuments() throws IOException {
+ Set<TextDocument> documents = new HashSet<TextDocument>();
+ RemoteDataProvider bibleByChapter = new RemoteDataProvider(
+ new URL("http://gold.linkeddata.org/data/bible/split_by_chapter.zip"));
+ File folder = bibleByChapter.getLocalDirectory();
+ for (File file : folder.listFiles()) {
+ if(!file.isDirectory() && !file.isHidden()){
+ try {
+ String text = Files.toString(file, Charsets.UTF_8);
+ documents.add(new TextDocument(text));
+ } catch (IOException e) {
+ e.printStackTrace();
+ }
+ }
+ }
+ return documents;
+ }
+
+
+ /**
* @throws java.lang.Exception
*/
@Before
@@ -153,7 +163,7 @@
lp.init();
semanticIndex = new SimpleSemanticIndex(ontology, syntacticIndex);
- semanticIndex.buildIndex(createDocuments());
+ semanticIndex.buildIndex(createBibleDocuments());
relevance = new PMIRelevanceMetric(semanticIndex);
@@ -209,10 +219,10 @@
ClassLearningProblem lp = new ClassLearningProblem(reasoner);
lp.setClassToDescribe(cls);
lp.init();
+
+ semanticIndex = new SimpleSemanticIndex(ontology, syntacticIndex, false);
+ semanticIndex.buildIndex(createBibleDocuments());
- semanticIndex = new SimpleSemanticIndex(ontology, syntacticIndex, false);
- semanticIndex.buildIndex(createDocuments());
-
relevance = new PMIRelevanceMetric(semanticIndex);
Map<Entity, Double> entityRelevance = RelevanceUtils.getRelevantEntities(cls, ontology, relevance);
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
