Java Code Examples for edu.stanford.nlp.ling.CoreLabel#word()

The following examples show how to use edu.stanford.nlp.ling.CoreLabel#word() . You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may check out the related API usage on the sidebar.
Example 1
Source File: Chapter4.java    From Natural-Language-Processing-with-Java-Second-Edition with MIT License 6 votes vote down vote up 
private static void usingStanfordNER() {
        String model = getModelDir() + "\\english.conll.4class.distsim.crf.ser.gz";
        CRFClassifier<CoreLabel> classifier = CRFClassifier.getClassifierNoExceptions(model);

        String sentence = "";
        for (String element : sentences) {
            sentence += element;
        }

        List<List<CoreLabel>> entityList = classifier.classify(sentence);

        for (List<CoreLabel> internalList : entityList) {
            for (CoreLabel coreLabel : internalList) {
                String word = coreLabel.word();
                String category = coreLabel.get(CoreAnnotations.AnswerAnnotation.class);
//                System.out.println(word + ":" + category);
                if (!"O".equals(category)) {
                    System.out.println(word + ":" + category);
                }

            }

        }
    }
Example 2
Source File: Chapter4.java    From Natural-Language-Processing-with-Java-Second-Edition with MIT License 6 votes vote down vote up 
private static void usingStanfordNER() {
        String model = getModelDir() + "\\english.conll.4class.distsim.crf.ser.gz";
        CRFClassifier<CoreLabel> classifier = CRFClassifier.getClassifierNoExceptions(model);

        String sentence = "";
        for (String element : sentences) {
            sentence += element;
        }

        List<List<CoreLabel>> entityList = classifier.classify(sentence);

        for (List<CoreLabel> internalList : entityList) {
            for (CoreLabel coreLabel : internalList) {
                String word = coreLabel.word();
                String category = coreLabel.get(CoreAnnotations.AnswerAnnotation.class);
//                System.out.println(word + ":" + category);
                if (!"O".equals(category)) {
                    System.out.println(word + ":" + category);
                }

            }

        }
    }
Example 3
Source File: EnglishReadability.java    From tint with GNU General Public License v3.0 5 votes vote down vote up 
@Override public void addingContentWord(CoreLabel token) {
        super.addingContentWord(token);

        String lemma = token.word();
        if (model.getLevel1Lemmas().contains(lemma)) {
            level1WordSize++;
        }
        if (model.getLevel2Lemmas().contains(lemma)) {
            level2WordSize++;
        }
        if (model.getLevel3Lemmas().contains(lemma)) {
            level3WordSize++;
        }
//        System.out.println("Adding content word (lemma): " + lemma);
//        System.out.println(model.getLevel1Lemmas().contains(lemma));
//        System.out.println(model.getLevel2Lemmas().contains(lemma));
//        System.out.println(model.getLevel3Lemmas().contains(lemma));
//        System.out.println();

//        HashMap<Integer, HashMultimap<String, String>> easyWords = model.getEasyWords();
//        String simplePos = getGenericPos(token.get(CoreAnnotations.PartOfSpeechAnnotation.class));
//        String lemma = token.get(CoreAnnotations.LemmaAnnotation.class);
//
//        if (easyWords.get(1).get(simplePos).contains(lemma)) {
//            level1WordSize++;
//        }
//        if (easyWords.get(2).get(simplePos).contains(lemma)) {
//            level2WordSize++;
//        }
//        if (easyWords.get(3).get(simplePos).contains(lemma)) {
//            level3WordSize++;
//        }
    }
Example 4
Source File: Readability.java    From tint with GNU General Public License v3.0 4 votes vote down vote up 
public void addWord(CoreLabel token) {
        token.set(ReadabilityAnnotations.ContentWord.class, false);
        token.set(ReadabilityAnnotations.LiteralWord.class, false);

        String pos = token.get(CoreAnnotations.PartOfSpeechAnnotation.class);
//        String lemma = token.get(CoreAnnotations.LemmaAnnotation.class);
        String word = token.word();

        addingToken(token);

        if (isWordPos(pos)) {
            addingWord(token);
            wordCount++;
            docLenLettersOnly += token.endPosition() - token.beginPosition();

            word = flattenToAscii(word);
            Hyphenation hyphenation = hyphenator.hyphenate(word);

            boolean done = false;
            if (hyphenation != null) {
                try {
                    String h = hyphenation.toString();
                    incrementHyphenCount(hyphenation.length() + 1);
                    token.set(ReadabilityAnnotations.HyphenationAnnotation.class, h);
                    done = true;
                    hyphenWordCount++;
                } catch (Exception e) {
                    // ignored
                }
            }

            if (!done && word.length() < 5) {
                incrementHyphenCount(1);
                hyphenWordCount++;
            }

            if (isContentPos(pos)) {
                contentWordSize++;
                addingContentWord(token);
            }
            if (isEasyPos(pos)) {
                contentEasyWordSize++;
                addingEasyWord(token);
            }
        }
        if (token.get(ReadabilityAnnotations.HyphenationAnnotation.class) == null) {
            token.set(ReadabilityAnnotations.HyphenationAnnotation.class, token.originalText());
        }

        String genericPos = getGenericPos(pos);
        posStats.add(pos);
        genericPosStats.add(genericPos);
    }