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

Example 1 with PlainToTokenParser

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

the class TestDiff method testDiff.

@Test
public void testDiff() {
    POSTagger tagger = new POSTagger();
    Parser parser = new PlainToTokenParser(new WordSplitter(new SentenceSplitter(testFile)));
    String sentence = "";
    int sentenceCounter = 0;
    int tokenCounter = 0;
    int correctCounter = 0;
    for (Token word = (Token) parser.next(); word != null; word = (Token) parser.next()) {
        String tag = tagger.discreteValue(word);
        if (refTags.get(tokenCounter).equals(tag)) {
            correctCounter++;
        }
        tokenCounter++;
    }
    double result = ((double) correctCounter) / tokenCounter;
    if (result < thresholdAcc) {
        fail("Tagger performance is insufficient: " + "\nProduced: " + result + "\nExpected: " + thresholdAcc);
    }
}

Example 2 with PlainToTokenParser

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

the class TestDiff method testDiff.

@Test
public void testDiff() {
    Chunker tagger = new Chunker();
    Parser parser = new PlainToTokenParser(new WordSplitter(new SentenceSplitter(testFile)));
    String previous = "";
    String sentence = "";
    int sentenceCounter = 0;
    for (Token w = (Token) parser.next(); w != null; w = (Token) parser.next()) {
        String prediction = tagger.discreteValue(w);
        if (prediction.startsWith("B-") || prediction.startsWith("I-") && !previous.endsWith(prediction.substring(2)))
            sentence += ("[" + prediction.substring(2) + " ");
        sentence += ("(" + w.partOfSpeech + " " + 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))))
            sentence += ("] ");
        if (w.next == null) {
            sentence = sentence.trim();
            String refSentence = refSentences.get(sentenceCounter).trim();
            if (!sentence.equals(refSentence))
                fail("Produced output doesn't match reference: " + "\nProduced: " + sentence + "\nExpected: " + refSentence);
            sentence = "";
            sentenceCounter++;
        }
        previous = prediction;
    }
}

Example 3 with PlainToTokenParser

use of edu.illinois.cs.cogcomp.lbjava.nlp.seg.PlainToTokenParser 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;
    }
}