Example usage for edu.stanford.nlp.classify LogisticClassifierFactory LogisticClassifierFactory

Introduction

In this page you can find the example usage for edu.stanford.nlp.classify LogisticClassifierFactory LogisticClassifierFactory.

Prototype

LogisticClassifierFactory

Source Link

Usage

From source file:knu.univ.lingvo.coref.SieveCoreferenceSystem.java

License:Open Source License

/**
 * Returns the name of the log file that this method writes.
 *//*  w w w  . j a v  a 2s .  co  m*/
public static String initializeAndRunCoref(Properties props) throws Exception {
    String timeStamp = Calendar.getInstance().getTime().toString().replaceAll("\\s", "-").replaceAll(":", "-");

    //
    // initialize logger
    //
    String logFileName = props.getProperty(Constants.LOG_PROP, "log.txt");
    if (logFileName.endsWith(".txt")) {
        logFileName = logFileName.substring(0, logFileName.length() - 4) + "_" + timeStamp + ".txt";
    } else {
        logFileName = logFileName + "_" + timeStamp + ".txt";
    }
    try {
        FileHandler fh = new FileHandler(logFileName, false);
        logger.addHandler(fh);
        logger.setLevel(Level.FINE);
        fh.setFormatter(new NewlineLogFormatter());
    } catch (SecurityException e) {
        System.err.println("ERROR: cannot initialize logger!");
        throw e;
    } catch (IOException e) {
        System.err.println("ERROR: cannot initialize logger!");
        throw e;
    }

    logger.fine(timeStamp);
    logger.fine(props.toString());
    Constants.printConstants(logger);

    // initialize coref system
    SieveCoreferenceSystem corefSystem = new SieveCoreferenceSystem(props);

    // MentionExtractor extracts MUC, ACE, or CoNLL documents
    MentionExtractor mentionExtractor = null;
    if (props.containsKey(Constants.MUC_PROP)) {
        mentionExtractor = new MUCMentionExtractor(corefSystem.dictionaries, props, corefSystem.semantics,
                corefSystem.singletonPredictor);
    } else if (props.containsKey(Constants.ACE2004_PROP) || props.containsKey(Constants.ACE2005_PROP)) {
        mentionExtractor = new ACEMentionExtractor(corefSystem.dictionaries, props, corefSystem.semantics,
                corefSystem.singletonPredictor);
    } else if (props.containsKey(Constants.CONLL2011_PROP)) {
        mentionExtractor = new CoNLLMentionExtractor(corefSystem.dictionaries, props, corefSystem.semantics,
                corefSystem.singletonPredictor);
    }
    if (mentionExtractor == null) {
        throw new RuntimeException("No input file specified!");
    }
    if (!Constants.USE_GOLD_MENTIONS) {
        // Set mention finder
        String mentionFinderClass = props.getProperty(Constants.MENTION_FINDER_PROP);
        if (mentionFinderClass != null) {
            String mentionFinderPropFilename = props.getProperty(Constants.MENTION_FINDER_PROPFILE_PROP);
            CorefMentionFinder mentionFinder;
            if (mentionFinderPropFilename != null) {
                Properties mentionFinderProps = new Properties();
                FileInputStream fis = new FileInputStream(mentionFinderPropFilename);
                mentionFinderProps.load(fis);
                fis.close();
                mentionFinder = (CorefMentionFinder) Class.forName(mentionFinderClass)
                        .getConstructor(Properties.class).newInstance(mentionFinderProps);
            } else {
                mentionFinder = (CorefMentionFinder) Class.forName(mentionFinderClass).newInstance();
            }
            mentionExtractor.setMentionFinder(mentionFinder);
        }
        if (mentionExtractor.mentionFinder == null) {
            logger.warning("No mention finder specified, but not using gold mentions");
        }
    }

    if (corefSystem.optimizeSieves && corefSystem.sieves.length > 1) {
        corefSystem.optimizeSieveOrdering(mentionExtractor, props, timeStamp);
    }

    try {
        runAndScoreCoref(corefSystem, mentionExtractor, props, timeStamp);
        LogisticClassifierFactory<Boolean, String> factory = new LogisticClassifierFactory<Boolean, String>();
        // Build a classifier
        LogisticClassifier<Boolean, String> classifier = factory
                .trainClassifier(((ClassifierSieve) corefSystem.sieves[0]).dataset, 0, 1e-15);
        // Check out the learned weights

        FileOutputStream fileOut = new FileOutputStream("classifier.ser");
        ObjectOutputStream out = new ObjectOutputStream(fileOut);
        out.writeObject(classifier);
        out.close();
        fileOut.close();
        System.out.printf("Serialized data is saved in /tmp/employee.ser");
    } catch (Exception ex) {
        logger.log(Level.SEVERE, "ERROR in running coreference", ex);
    }
    logger.info("done");
    String endTimeStamp = Calendar.getInstance().getTime().toString().replaceAll("\\s", "-");
    logger.fine(endTimeStamp);

    return logFileName;
}

---