Example usage for edu.stanford.nlp.ling CoreLabel setEndPosition

Introduction

In this page you can find the example usage for edu.stanford.nlp.ling CoreLabel setEndPosition.

Prototype

@Override
public void setEndPosition(int endPos) 

Source Link

Usage

From source file:conditionalCFG.ConditionalCFGParser.java

License:Open Source License

private CoreLabel getCoreLabel(int labelIndex) {
    if (originalCoreLabels[labelIndex] != null) {
        CoreLabel terminalLabel = originalCoreLabels[labelIndex];
        if (terminalLabel.value() == null && terminalLabel.word() != null) {
            terminalLabel.setValue(terminalLabel.word());
        }//www . j  a  va 2  s . c  o m
        return terminalLabel;
    }

    String wordStr = wordIndex.get(words[labelIndex]);
    CoreLabel terminalLabel = new CoreLabel();
    terminalLabel.setValue(wordStr);
    terminalLabel.setWord(wordStr);
    terminalLabel.setBeginPosition(beginOffsets[labelIndex]);
    terminalLabel.setEndPosition(endOffsets[labelIndex]);
    if (originalTags[labelIndex] != null) {
        terminalLabel.setTag(originalTags[labelIndex].tag());
    }
    return terminalLabel;
}

---

From source file:de.l3s.workive.analysis.ner.GermanNER.java

public List<Entity> extractEntities(CoreMap sentence) {
    List<Entity> entityList = new ArrayList<Entity>();

    CoreLabel prevEntity = null;
    String tag = "";

    for (CoreLabel token : sentence.get(TokensAnnotation.class)) {
        String entityTag = token.get(NamedEntityTagAnnotation.class);

        //System.out.println(entityTag);
        if (entityTag.compareToIgnoreCase("I-ORG") == 0 || entityTag.compareToIgnoreCase("I-PER") == 0
                || entityTag.compareToIgnoreCase("I-LOC") == 0 || entityTag.compareToIgnoreCase("MISC") == 0) {

            if (prevEntity != null) {
                if (prevEntity.get(NamedEntityTagAnnotation.class).compareToIgnoreCase(entityTag) == 0
                        && prevEntity.endPosition() == token.beginPosition() - 1) {
                    prevEntity.setEndPosition(token.endPosition());
                    prevEntity.set(TextAnnotation.class,
                            prevEntity.get(TextAnnotation.class) + " " + token.get(TextAnnotation.class));
                } else {
                    Triple<String, Integer, Integer> triple = new Triple<String, Integer, Integer>(
                            prevEntity.get(TextAnnotation.class), prevEntity.beginPosition(),
                            prevEntity.endPosition());
                    entityList.add(new Entity(triple, tag));
                    prevEntity = token;//  w  ww.  ja v a 2  s.com
                    tag = entityTag;

                }
            } else {
                prevEntity = token;
                tag = entityTag;
            }
        }
    }

    if (prevEntity != null) {

        Triple<String, Integer, Integer> triple = new Triple<String, Integer, Integer>(
                prevEntity.get(TextAnnotation.class), prevEntity.beginPosition(), prevEntity.endPosition());
        entityList.add(new Entity(triple, tag));
        tag = "";
    }
    return entityList;
}

---

From source file:de.tudarmstadt.ukp.dkpro.core.stanfordnlp.util.CoreNlpUtils.java

License:Open Source License

public static CoreLabel tokenToWord(Token aToken) {
    CoreLabel t = new CoreLabel();

    t.setOriginalText(aToken.getCoveredText());
    t.setWord(aToken.getCoveredText());//from  w ww  . j  av a2  s.c  o m
    t.setBeginPosition(aToken.getBegin());
    t.setEndPosition(aToken.getEnd());

    if (aToken.getLemma() != null) {
        t.setLemma(aToken.getLemma().getValue());
    }

    if (aToken.getPos() != null) {
        t.setTag(aToken.getPos().getPosValue());
    }

    return t;
}

---

From source file:edu.cmu.ml.rtw.users.ssrivastava.RegexExtractor.java

public static CoreMap getStanfordSentence(DocumentNLP document, int sentIdx) {
    List<String> words = document.getSentenceTokenStrs(sentIdx);
    List<PoSTag> posTags = document.getSentencePoSTags(sentIdx);

    List<CoreLabel> tokenList = new ArrayList<CoreLabel>();
    for (int i = 0; i < words.size(); i++) {
        /*Re-create Stanford tokens*/
        CoreLabel token = new CoreLabel();
        token.setWord(words.get(i));//  www  . jav a  2  s  .c  om
        token.setTag(posTags.get(i).toString());
        token.setNER("O");
        token.setDocID(document.getName());
        token.setSentIndex(sentIdx);
        token.setBeginPosition(document.getToken(sentIdx, i).getCharSpanStart());
        token.setEndPosition(document.getToken(sentIdx, i).getCharSpanEnd());

        //System.out.println(token.word()+" "+token.beginPosition()+" "+token.endPosition());
        tokenList.add(token);
    }

    //Add NER labels for sentence
    List<Pair<TokenSpan, String>> ners = document.getNer(sentIdx);
    for (Pair<TokenSpan, String> p : ners) {
        for (int k = p.getFirst().getStartTokenIndex(); k < p.getFirst().getEndTokenIndex(); k++) {
            tokenList.get(k).setNER(p.getSecond());
        }
    }

    //Convert to Stanford Sentence
    CoreMap sentence = new ArrayCoreMap();
    sentence.set(TokensAnnotation.class, tokenList);
    sentence.set(CharacterOffsetBeginAnnotation.class, tokenList.get(0).beginPosition());
    sentence.set(CharacterOffsetEndAnnotation.class, tokenList.get(words.size() - 1).endPosition());
    return sentence;
}

---

From source file:NER.NERAnnotation.java

public List<Entity> extractEntities(CoreMap sentence) {
    List<Entity> entityList = new ArrayList<Entity>();

    CoreLabel prevEntity = null;
    String tag = "";

    for (CoreLabel token : sentence.get(TokensAnnotation.class)) {
        String entityTag = token.get(NamedEntityTagAnnotation.class);

        //System.out.println(entityTag);
        if (entityTag.compareToIgnoreCase("LOCATION") == 0 || entityTag.compareToIgnoreCase("DATE") == 0
                || entityTag.compareToIgnoreCase("PERSON") == 0
                || entityTag.compareToIgnoreCase("ORGANIZATION") == 0
                || entityTag.compareToIgnoreCase("MISC") == 0) {

            if (prevEntity != null) {
                if (prevEntity.get(NamedEntityTagAnnotation.class).compareToIgnoreCase(entityTag) == 0
                        && prevEntity.endPosition() == token.beginPosition() - 1) {
                    prevEntity.setEndPosition(token.endPosition());
                    prevEntity.set(TextAnnotation.class,
                            prevEntity.get(TextAnnotation.class) + " " + token.get(TextAnnotation.class));
                    // tag=entityTag;

                    // System.out.println(entityTag);
                } else {
                    Triple<String, Integer, Integer> triple = new Triple<String, Integer, Integer>(
                            prevEntity.get(TextAnnotation.class), prevEntity.beginPosition(),
                            prevEntity.endPosition());
                    entityList.add(new Entity(triple, tag));
                    prevEntity = token;/*from   ww  w. j  a v  a  2s.c o  m*/
                    tag = entityTag;

                }
            } else {
                prevEntity = token;
                tag = entityTag;
                //System.out.println(entityTag);
            }
        }
    }

    if (prevEntity != null) {

        Triple<String, Integer, Integer> triple = new Triple<String, Integer, Integer>(
                prevEntity.get(TextAnnotation.class), prevEntity.beginPosition(), prevEntity.endPosition());
        entityList.add(new Entity(triple, tag));
        tag = "";
        // System.out.println(tag);
    }

    return entityList;
}

---