Examples with SentenceSplitter edu.illinois.cs.cogcomp.lbjava.nlp.SentenceSplitter used on opensource projects

Example 11 with SentenceSplitter

use of edu.illinois.cs.cogcomp.lbjava.nlp.SentenceSplitter in project cogcomp-nlp by CogComp.

the class ChunksAndPOSTags method main.

public static void main(String[] args) {
    String filename = null;
    try {
        filename = args[0];
        if (args.length > 1)
            throw new Exception();
    } catch (Exception e) {
        System.err.println("usage: java edu.illinois.cs.cogcomp.chunker.main.ChunksAndPOSTags <input file>");
        System.exit(1);
    }
    Chunker chunker = new Chunker();
    Parser parser = new PlainToTokenParser(new WordSplitter(new SentenceSplitter(filename)));
    String previous = "";
    for (Word w = (Word) parser.next(); w != null; w = (Word) parser.next()) {
        String prediction = chunker.discreteValue(w);
        if (prediction.startsWith("B-") || prediction.startsWith("I-") && !previous.endsWith(prediction.substring(2)))
            logger.info("[" + prediction.substring(2) + " ");
        logger.info("(" + w.partOfSpeech + " " + w.form + ") ");
        if (!prediction.equals("O") && (w.next == null || chunker.discreteValue(w.next).equals("O") || chunker.discreteValue(w.next).startsWith("B-") || !chunker.discreteValue(w.next).endsWith(prediction.substring(2))))
            logger.info("] ");
        if (w.next == null)
            logger.info("\n");
        previous = prediction;
    }
}

Example 12 with SentenceSplitter

use of edu.illinois.cs.cogcomp.lbjava.nlp.SentenceSplitter in project cogcomp-nlp by CogComp.

the class SegmentTagPlain method main.

public static void main(String[] args) {
    String taggerName = null;
    String inputFile = null;
    String parserName = null;
    try {
        taggerName = args[0];
        inputFile = args[1];
        if (args.length > 2) {
            parserName = args[2];
            if (args.length > 3)
                throw new Exception();
        }
    } catch (Exception e) {
        System.err.println("usage: java edu.illinois.cs.cogcomp.lbjava.edu.illinois.cs.cogcomp.lbjava.nlp.seg.SegmentTagPlain <word classifier> " + "<input file> \\\n" + "                                         [<parser>]");
        System.exit(1);
    }
    Classifier tagger = ClassUtils.getClassifier(taggerName);
    Parser parser;
    if (parserName == null)
        parser = new PlainToTokenParser(new WordSplitter(new SentenceSplitter(inputFile)));
    else
        parser = ClassUtils.getParser(parserName, new Class[] { Parser.class }, new Parser[] { new WordSplitter(new SentenceSplitter(inputFile)) });
    String previous = "";
    for (Word w = (Word) parser.next(); w != null; w = (Word) parser.next()) {
        String prediction = tagger.discreteValue(w);
        if (prediction.startsWith("B-") || prediction.startsWith("I-") && !previous.endsWith(prediction.substring(2)))
            System.out.print("[" + prediction.substring(2) + " ");
        System.out.print(w.form + " ");
        if (!prediction.equals("O") && (w.next == null || tagger.discreteValue(w.next).equals("O") || tagger.discreteValue(w.next).startsWith("B-") || !tagger.discreteValue(w.next).endsWith(prediction.substring(2))))
            System.out.print("] ");
        if (w.next == null)
            System.out.println();
        previous = prediction;
    }
}