Java MaltParserService类代码示例

import org.maltparser.MaltParserService; //导入依赖的package包/类
@Override
public void initialize(UimaContext context) throws ResourceInitializationException {
  super.initialize(context);
  try {
    OptionManager.instance().loadOptionDescriptionFile();
    OptionManager.instance().getOptionDescriptions().generateMaps();
    this.service = new MaltParserService();
    File modelFile = new File(this.modelFileName);
    String fileName = modelFile.getName();
    String workingDirectory = modelFile.getParent();
    String command = String.format("-c %s -m parse -w %s", fileName, workingDirectory);
    this.service.initializeParserModel(command);
  } catch (MaltChainedException e) {
    throw new ResourceInitializationException(e);
  }
}
 

import org.maltparser.MaltParserService; //导入依赖的package包/类
public ParserMalt(){
	
	try {

		Properties props = new Properties();
		props.put("customAnnotatorClass.cleanprefix", "ca.ualberta.exemplar.core.CleanPrefixAnnotator");
		props.put("customAnnotatorClass.locationjuxtaposition", "ca.ualberta.exemplar.core.LocationJuxtapositionAnnotator");
		props.put("customAnnotatorClass.removedashes", "ca.ualberta.exemplar.core.RemoveDashesAnnotator");
		props.put("annotators", "tokenize, ssplit, removedashes, pos, lemma, ner, cleanprefix, locationjuxtaposition");
		pipeline = new StanfordCoreNLP(props);

		maltParser = new MaltParserService();
		maltParser.initializeParserModel("-c " + Paths.MALT_PARSER_FILENAME
				+ " -w " + Paths.MALT_PARSER_DIRECTORY + " -m parse");
		
		// Used to map from malt relations to Stanford relations
		relationMap = new HashMap<String,String>();
		relationMap.put("measure", "npadvmod");

	} catch (Exception e) {
		e.printStackTrace();
	}
}
 

import org.maltparser.MaltParserService; //导入依赖的package包/类
/**
 * @param args
 */
public static void main(String[] args) {
	try {
		String trainingDataFile = ".."+File.separator+"data"+File.separator+"talbanken05_train.conll";
		// Trains the parser model model0.mco and uses the option container 0
		new MaltParserService(0).runExperiment("-c model0 -i "+trainingDataFile+" -m learn -ne true -nr false");
		// Trains the parser model model1.mco and uses the option container 1
		new MaltParserService(1).runExperiment("-c model1 -i "+trainingDataFile+" -m learn -ne true -nr true");
	} catch (MaltChainedException e) {
		System.err.println("MaltParser exception : " + e.getMessage());
	}
}
 

import org.maltparser.MaltParserService; //导入依赖的package包/类
public static void main(String[] args) {
	if (args.length != 1) {
		System.out.println("Usage: ");
		System.out.println(" java -cp classes:../../malt.jar org.maltparser.examples.OptionFreeInitialization <data format file>");
		System.out.println("Example: ");
		System.out.println(" java -cp classes:../../malt.jar org.maltparser.examples.OptionFreeInitialization ../../appdata/dataformat/conllx.xml");
		return;
	}
	try {
		// Create a MaltParserService object without option manager
		MaltParserService service =  new MaltParserService(true);
		// Creates an array of tokens, which contains the Swedish sentence 'Grundavdraget upphör alltså vid en taxerad inkomst på 52500 kr.'
		// in the CoNLL data format.
		String[] tokens = new String[11];
		tokens[0] = "1\tGrundavdraget\t_\tN\tNN\tDD|SS\t2\tSS";
		tokens[1] = "2\tupphör\t_\tV\tVV\tPS|SM\t0\tROOT";
		tokens[2] = "3\talltså\t_\tAB\tAB\tKS\t2\t+A";
		tokens[3] = "4\tvid\t_\tPR\tPR\t_\t2\tAA";
		tokens[4] = "5\ten\t_\tN\tEN\t_\t7\tDT";
		tokens[5] = "6\ttaxerad\t_\tP\tTP\tPA\t7\tAT";
		tokens[6] = "7\tinkomst\t_\tN\tNN\t_\t4\tPA";
		tokens[7] = "8\tpå\t_\tPR\tPR\t_\t7\tET";
		tokens[8] = "9\t52500\t_\tR\tRO\t_\t10\tDT";
		tokens[9] = "10\tkr\t_\tN\tNN\t_\t8\tPA";
		tokens[10] = "11\t.\t_\tP\tIP\t_\t2\tIP";
		// Print out the string array
		for (int i = 0; i < tokens.length; i++) {
			System.out.println(tokens[i]);
		}
		// Reads the data format specification file
		DataFormatSpecification dataFormatSpecification = service.readDataFormatSpecification(args[0]);
		// Use the data format specification file to build a dependency structure based on the string array
		DependencyStructure graph = service.toDependencyStructure(tokens, dataFormatSpecification);
		// Print the dependency structure
		System.out.println(graph);
	} catch (MaltChainedException e) {
		System.err.println("MaltParser exception: " + e.getMessage());
	}
}
 

import org.maltparser.MaltParserService; //导入依赖的package包/类
/**
 * @param args
 */
public static void main(String[] args) {
	try {
		MaltParserService service =  new MaltParserService();
		// Inititalize the parser model 'model0' and sets the working directory to '.' and sets the logging file to 'parser.log'
		service.initializeParserModel("-c model0 -m parse -w . -lfi parser.log");
		
		// Creates an array of tokens, which contains the Swedish sentence 'Grundavdraget upphör alltså vid en taxerad inkomst på 52500 kr.'
		// in the CoNLL data format.
		String[] tokens = new String[11];
		tokens[0] = "1\tGrundavdraget\t_\tN\tNN\tDD|SS";
		tokens[1] = "2\tupphör\t_\tV\tVV\tPS|SM";
		tokens[2] = "3\talltså\t_\tAB\tAB\tKS";
		tokens[3] = "4\tvid\t_\tPR\tPR\t_";
		tokens[4] = "5\ten\t_\tN\tEN\t_";
		tokens[5] = "6\ttaxerad\t_\tP\tTP\tPA";
		tokens[6] = "7\tinkomst\t_\tN\tNN\t_";
		tokens[7] = "8\tpå\t_\tPR\tPR\t_";
		tokens[8] = "9\t52500\t_\tR\tRO\t_";
		tokens[9] = "10\tkr\t_\tN\tNN\t_";
		tokens[10] = "11\t.\t_\tP\tIP\t_";
		// Parses the Swedish sentence above
		String[] outputTokens = service.parseTokens(tokens);
		// Outputs the with the head index and dependency type information
		for (int i = 0; i < outputTokens.length; i++) {
			System.out.println(outputTokens[i]);
		}
		// Terminates the parser model
		service.terminateParserModel();
	} catch (MaltChainedException e) {
		System.err.println("MaltParser exception: " + e.getMessage());
	}
}
 

import org.maltparser.MaltParserService; //导入依赖的package包/类
/**
 * @param args
 */
public static void main(String[] args) {
	try {
		MaltParserService service =  new MaltParserService();
		// Inititalize the parser model 'model0' and sets the working directory to '.' and sets the logging file to 'parser.log'
		service.initializeParserModel("-c model0 -m parse -w . -lfi parser.log");
		
		// Creates an array of tokens, which contains the Swedish sentence 'Grundavdraget upphör alltså vid en taxerad inkomst på 52500 kr.'
		// in the CoNLL data format.
		String[] tokens = new String[11];
		tokens[0] = "1\tGrundavdraget\t_\tN\tNN\tDD|SS";
		tokens[1] = "2\tupphör\t_\tV\tVV\tPS|SM";
		tokens[2] = "3\talltså\t_\tAB\tAB\tKS";
		tokens[3] = "4\tvid\t_\tPR\tPR\t_";
		tokens[4] = "5\ten\t_\tN\tEN\t_";
		tokens[5] = "6\ttaxerad\t_\tP\tTP\tPA";
		tokens[6] = "7\tinkomst\t_\tN\tNN\t_";
		tokens[7] = "8\tpå\t_\tPR\tPR\t_";
		tokens[8] = "9\t52500\t_\tR\tRO\t_";
		tokens[9] = "10\tkr\t_\tN\tNN\t_";
		tokens[10] = "11\t.\t_\tP\tIP\t_";
		// Parses the Swedish sentence above
		DependencyStructure graph = service.parse(tokens);
		// Outputs the dependency graph created by MaltParser.
		System.out.println(graph);
		// Terminates the parser model
		service.terminateParserModel();
	} catch (MaltChainedException e) {
		System.err.println("MaltParser exception: " + e.getMessage());
	}
}
 

import org.maltparser.MaltParserService; //导入依赖的package包/类
/**
 * @param args
 */
public static void main(String[] args) {
	try {
		MaltParserService service =  new MaltParserService();
		// Inititalize the parser model 'model0' and sets the working directory to '.' and sets the logging file to 'parser.log'
		service.initializeParserModel("-u jar:file:mco_nested_in_jar.jar!/model0.mco -m parse -w . -lfi parser.log -v debug");

		// Creates an array of tokens, which contains the Swedish sentence 'Grundavdraget upphör alltså vid en taxerad inkomst på 52500 kr.'
		// in the CoNLL data format.
		String[] tokens = new String[11];
		tokens[0] = "1\tGrundavdraget\t_\tN\tNN\tDD|SS";
		tokens[1] = "2\tupphör\t_\tV\tVV\tPS|SM";
		tokens[2] = "3\talltså\t_\tAB\tAB\tKS";
		tokens[3] = "4\tvid\t_\tPR\tPR\t_";
		tokens[4] = "5\ten\t_\tN\tEN\t_";
		tokens[5] = "6\ttaxerad\t_\tP\tTP\tPA";
		tokens[6] = "7\tinkomst\t_\tN\tNN\t_";
		tokens[7] = "8\tpå\t_\tPR\tPR\t_";
		tokens[8] = "9\t52500\t_\tR\tRO\t_";
		tokens[9] = "10\tkr\t_\tN\tNN\t_";
		tokens[10] = "11\t.\t_\tP\tIP\t_";
		// Parses the Swedish sentence above
		String[] outputTokens = service.parseTokens(tokens);
		// Outputs the with the head index and dependency type information
		for (int i = 0; i < outputTokens.length; i++) {
			System.out.println(outputTokens[i]);
		}
		// Terminates the parser model
		service.terminateParserModel();
	} catch (MaltChainedException e) {
		System.err.println("MaltParser exception: " + e.getMessage());
		e.printStackTrace();
	}
}
 

import org.maltparser.MaltParserService; //导入依赖的package包/类
/**
 * @param args
 */
public static void main(String[] args) {
	try {
		String testDataFile = ".."+File.separator+"data"+File.separator+"talbanken05_test.conll";
		// Parses the test data file using the parser model model0.mco and using the option container 0
		new MaltParserService(0).runExperiment("-c model0 -i "+testDataFile+" -o out1.conll -m parse");
		// Parses the test data file using the parser model model1.mco and using the option container 1
		new MaltParserService(1).runExperiment("-c model1 -i "+testDataFile+" -o out2.conll -m parse");
	} catch (MaltChainedException e) {
		System.err.println("MaltParser exception : " + e.getMessage());
	}
}