Menu
▾
▴
[DL-Learner SVN] SF.net SVN: dl-learner:[2670] trunk
|
From: <lor...@us...> - 2011-02-27 08:16:17
|
Revision: 2670
http://dl-learner.svn.sourceforge.net/dl-learner/?rev=2670&view=rev
Author: lorenz_b
Date: 2011-02-27 08:16:11 +0000 (Sun, 27 Feb 2011)
Log Message:
-----------
Inluded Lucene search into script.
Modified Paths:
--------------
trunk/autosparql/src/main/java/org/dllearner/autosparql/evaluation/EvaluationWithNLQueriesScript.java
trunk/autosparql/src/main/java/org/dllearner/autosparql/server/ExampleFinder.java
trunk/autosparql/src/main/java/org/dllearner/autosparql/server/search/LuceneSearch.java
trunk/sparql-query-generator/src/main/java/org/dllearner/sparqlquerygenerator/cache/QueryTreeCache.java
Modified: trunk/autosparql/src/main/java/org/dllearner/autosparql/evaluation/EvaluationWithNLQueriesScript.java
===================================================================
--- trunk/autosparql/src/main/java/org/dllearner/autosparql/evaluation/EvaluationWithNLQueriesScript.java 2011-02-26 23:08:56 UTC (rev 2669)
+++ trunk/autosparql/src/main/java/org/dllearner/autosparql/evaluation/EvaluationWithNLQueriesScript.java 2011-02-27 08:16:11 UTC (rev 2670)
@@ -61,6 +61,7 @@
import org.dllearner.sparqlquerygenerator.operations.lgg.LGGGeneratorImpl;
import org.dllearner.sparqlquerygenerator.util.ExactMatchFilter;
import org.dllearner.sparqlquerygenerator.util.QuestionBasedStatementFilter;
+import org.dllearner.sparqlquerygenerator.util.QuestionBasedStatementSelector;
import org.w3c.dom.DOMException;
import org.w3c.dom.Document;
import org.w3c.dom.Element;
@@ -193,6 +194,14 @@
return resources;
}
+ private List<String> getResourcesByNLQueryWithLucene(String question){
+ logger.info("Getting Top " + TOP_K + " resources related to question with Lucene...");
+ List<String> resources = luceneSearch.getResources(question);
+ logger.info("Got " + resources.size() + " resources:");
+ logger.info(resources);
+ return resources;
+ }
+
private List<String> getRelevantWords(String question){
return qProcessor.getRelevantWords(question);
// Properties props = new Properties();
@@ -274,7 +283,7 @@
Set<String> relatedResources;
List<String> relevantWords;
int i = 1;
- for(String question : question2Answers.keySet()){
+ for(String question : question2Answers.keySet()){question = "Give me all films with Tom Cruise!";
logger.info(getNewQuestionString(i++, question));
try {
logger.info("Evaluating question \"" + question + "\"...");
@@ -285,6 +294,7 @@
//preprocess question to extract only relevant words and set them as filter for statements
relevantWords = getRelevantWords(question);
exFinder.setStatementFilter(new QuestionBasedStatementFilter(new HashSet<String>(relevantWords)));
+// exFinder.setStatementSelector(new QuestionBasedStatementSelector(new HashSet<String>(relevantWords)));
//expand with synonyms
if(USE_SYNONYMS){
relevantWords.addAll(getSynonyms(relevantWords));
@@ -296,8 +306,11 @@
}
question.trim();
logger.info("Rebuilt question string: " + question);
+
//get examples
- examples = getResourcesByWikipedia(question);//luceneSearch.getResources(question)
+// examples = getResourcesByWikipedia(question);
+ examples = getResourcesByNLQueryWithLucene(question);
+
//get resources which are relevant for query and add them as filter for objects
// relatedResources = getResourcesByNLQuery(question.substring(0, question.length()-1));
// relatedResources.addAll(getSchemaElementsByQuery(question.substring(0, question.length()-1)));
Modified: trunk/autosparql/src/main/java/org/dllearner/autosparql/server/ExampleFinder.java
===================================================================
--- trunk/autosparql/src/main/java/org/dllearner/autosparql/server/ExampleFinder.java 2011-02-26 23:08:56 UTC (rev 2669)
+++ trunk/autosparql/src/main/java/org/dllearner/autosparql/server/ExampleFinder.java 2011-02-27 08:16:11 UTC (rev 2670)
@@ -31,6 +31,7 @@
import com.hp.hpl.jena.query.ResultSetRewindable;
import com.hp.hpl.jena.rdf.model.Model;
import com.hp.hpl.jena.rdf.model.Selector;
+import com.hp.hpl.jena.rdf.model.Statement;
import com.hp.hpl.jena.vocabulary.RDFS;
public class ExampleFinder {
@@ -455,10 +456,14 @@
queryTreeCache.setObjectFilter(filter);
}
- public void setStatementFilter(Selector filter){
+ public void setStatementFilter(com.hp.hpl.jena.util.iterator.Filter<Statement> filter){
queryTreeCache.setStatementFilter(filter);
}
+ public void setStatementSelector(Selector selector){
+ queryTreeCache.setStatementSelector(selector);
+ }
+
public String getCurrentQuery(){
return currentQuery;
}
Modified: trunk/autosparql/src/main/java/org/dllearner/autosparql/server/search/LuceneSearch.java
===================================================================
--- trunk/autosparql/src/main/java/org/dllearner/autosparql/server/search/LuceneSearch.java 2011-02-26 23:08:56 UTC (rev 2669)
+++ trunk/autosparql/src/main/java/org/dllearner/autosparql/server/search/LuceneSearch.java 2011-02-27 08:16:11 UTC (rev 2670)
@@ -2,6 +2,7 @@
import java.io.File;
import java.io.IOException;
+import java.text.NumberFormat.Field;
import java.util.ArrayList;
import java.util.List;
@@ -15,6 +16,8 @@
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
+import org.apache.lucene.search.Sort;
+import org.apache.lucene.search.SortField;
import org.apache.lucene.search.TopScoreDocCollector;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
@@ -36,7 +39,7 @@
Directory dir = FSDirectory.open(new File(indexDirectory));//RAMDirectory();
searcher = new IndexSearcher(dir, true);
Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_30);
- queryParser = new QueryParser(Version.LUCENE_30, "abstract", analyzer);
+ queryParser = new QueryParser(Version.LUCENE_30, "comment", analyzer);
collector = TopScoreDocCollector.create(hitsPerPage, true);
} catch (CorruptIndexException e) {
e.printStackTrace();
@@ -54,6 +57,7 @@
try {
Query query = queryParser.parse(queryString);
searcher.search(query, collector);
+// System.out.println(searcher.search(query, null, 10, new Sort(new SortField("pagerank", SortField.INT))));
ScoreDoc[] hits = collector.topDocs(offset).scoreDocs;
for(ScoreDoc doc : hits) {
Modified: trunk/sparql-query-generator/src/main/java/org/dllearner/sparqlquerygenerator/cache/QueryTreeCache.java
===================================================================
--- trunk/sparql-query-generator/src/main/java/org/dllearner/sparqlquerygenerator/cache/QueryTreeCache.java 2011-02-26 23:08:56 UTC (rev 2669)
+++ trunk/sparql-query-generator/src/main/java/org/dllearner/sparqlquerygenerator/cache/QueryTreeCache.java 2011-02-27 08:16:11 UTC (rev 2670)
@@ -11,6 +11,7 @@
import com.hp.hpl.jena.rdf.model.Model;
import com.hp.hpl.jena.rdf.model.Resource;
import com.hp.hpl.jena.rdf.model.Selector;
+import com.hp.hpl.jena.rdf.model.Statement;
public class QueryTreeCache {
@@ -46,10 +47,14 @@
factory.setObjectFilter(filter);
}
- public void setStatementFilter(Selector filter){
- factory.setStatementSelector(filter);
+ public void setStatementFilter(com.hp.hpl.jena.util.iterator.Filter<Statement> filter){
+ factory.setStatementFilter(filter);
}
+ public void setStatementSelector(Selector selector){
+ factory.setStatementSelector(selector);
+ }
+
public void clear(){
cache.clear();
}
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
