de.tudarmstadt.ukp.dkpro.core.api.segmentation.type.Sentence类的使用及代码示例

x33g5p2x  于2022-01-30 转载在 其他  
字(10.0k)|赞(0)|评价(0)|浏览(129)

本文整理了Java中de.tudarmstadt.ukp.dkpro.core.api.segmentation.type.Sentence类的一些代码示例，展示了Sentence类的具体用法。这些代码示例主要来源于Github/Stackoverflow/Maven等平台，是从一些精选项目中提取出来的代码，具有较强的参考意义，能在一定程度帮忙到你。Sentence类的具体详情如下：
包路径：de.tudarmstadt.ukp.dkpro.core.api.segmentation.type.Sentence
类名称：Sentence

Sentence介绍

[英]Updated by JCasGen Thu Feb 28 07:53:35 UTC 2019 XML source: /usr/src/mvn_workdir/dkpro-core-api-segmentation-asl/target/jcasgen/typesystem.xml
[中]JCasGen Thu于2019年2月28日07:53:35 UTC XML source:/usr/src/mvn_workdir/dkpro核心api分段asl/target/JCasGen/typesystem更新。xml

代码示例

代码示例来源：origin: de.tudarmstadt.ukp.clarin.webanno/de.tudarmstadt.ukp.clarin.webanno.tsv

Sentence outSentence = new Sentence(aJCas);
  outSentence.setBegin(tokensStored.get("t_" + firstTokenInSentence.get(i)).getEnd());
  outSentence.setEnd(tokensStored.get("t_" + (tokensStored.size())).getEnd());
  outSentence.addToIndexes();
  break;
  outSentence.setBegin(tokensStored.get("t_" + firstTokenInSentence.get(i))
      .getBegin());
  outSentence.setEnd(tokensStored.get("t_" + (tokensStored.size())).getEnd());
  outSentence.addToIndexes();
  outSentence.setBegin(tokensStored.get("t_" + firstTokenInSentence.get(i))
      .getBegin());
  outSentence.setEnd(tokensStored.get("t_" + firstTokenInSentence.get(i + 1))
      .getEnd());
  outSentence.addToIndexes();
      .setBegin(tokensStored.get("t_" + firstTokenInSentence.get(i)).getEnd() + 1);
  outSentence.setEnd(tokensStored.get("t_" + firstTokenInSentence.get(i + 1))
      .getEnd());
  outSentence.addToIndexes();

代码示例来源：origin: de.tudarmstadt.ukp.clarin.webanno/de.tudarmstadt.ukp.clarin.webanno.brat

/**
 * Get the cureent sentence based on the anotation begin/end offset
 */
public static Sentence getCurrentSentence(JCas aJCas, int aBegin, int aEnd){
  Sentence currentSentence = null;
  for(Sentence sentence :select(aJCas, Sentence.class)){
    if(sentence.getBegin()<=aBegin && sentence.getEnd()>=aEnd){
      currentSentence = sentence;
      break;
    }
  }
  return currentSentence;
}

代码示例来源：origin: de.tudarmstadt.ukp.clarin.webanno/de.tudarmstadt.ukp.clarin.webanno.brat

Sentence.class,
    BratAjaxCasUtil.getLastSentenceAddressInDisplayWindow(jCas,
        firstSentence.getAddress(), windowSize));
begin = firstSentence.getBegin();
end = lastSentence.getEnd();
sentenceNumber = BratAjaxCasUtil.getFirstSentenceNumber(jCas, firstSentence.getAddress());
segmentAdress.put(username, new HashMap<Integer, Integer>());
  segmentBeginEnd.put(sentence.getBegin(), sentence.getEnd());
  segmentText.put(sentence.getBegin(), sentence.getCoveredText().toString());
  segmentNumber.put(sentence.getBegin(), sentenceNumber);
  segmentAdress.get(username).put(sentence.getBegin(), sentence.getAddress());

代码示例来源：origin: de.tudarmstadt.ukp.dkpro.core/de.tudarmstadt.ukp.dkpro.core.api.segmentation-asl

/** @generated
 * @param jcas JCas to which this Feature Structure belongs
 * @param begin offset to the begin spot in the SofA
 * @param end offset to the end spot in the SofA 
*/  
public Sentence(JCas jcas, int begin, int end) {
 super(jcas);
 setBegin(begin);
 setEnd(end);
 readObject();
}

代码示例来源：origin: dkpro/dkpro-tc

protected void setSentence(JCas aJCas, int begin, int end)
{
  Sentence sentence = new Sentence(aJCas, begin, end);
  sentence.addToIndexes();
}

代码示例来源：origin: de.tudarmstadt.ukp.clarin.webanno/webanno-api-dao

public static void tokenize(JCas aJCas)
{
  BreakIterator bi = BreakIterator.getWordInstance(Locale.US);
  for (Sentence s : select(aJCas, Sentence.class)) {
    bi.setText(s.getCoveredText());
    int last = bi.first();
    int cur = bi.next();
    while (cur != BreakIterator.DONE) {
      int[] span = new int[] { last, cur };
      trim(s.getCoveredText(), span);
      if (!isEmpty(span[0], span[1])) {
        Token seg = new Token(aJCas, span[0] + s.getBegin(), span[1] + s.getBegin());
        seg.addToIndexes(aJCas);
      }
      last = cur;
      cur = bi.next();
    }
  }
}

代码示例来源：origin: webanno/webanno

private static JCas makeJCasOneSentence(String aText) throws UIMAException
{
  JCas jcas = makeJCas();
  
  TokenBuilder<Token, Sentence> tb = new TokenBuilder<>(Token.class,
      Sentence.class);
  tb.buildTokens(jcas, aText);
  
  // Remove the sentences generated by the token builder which treats the line break as a
  // sentence break
  for (Sentence s : select(jcas, Sentence.class)) {
    s.removeFromIndexes();
  }
  
  // Add a new sentence covering the whole text
  new Sentence(jcas, 0, jcas.getDocumentText().length()).addToIndexes();
  
  return jcas;
}

代码示例来源：origin: de.tudarmstadt.ukp.clarin.webanno/de.tudarmstadt.ukp.clarin.webanno.brat

private static int getLastSentenceAddress(BratAnnotatorModel aBratAnnotatorModel, JCas jCas,
    JCas userJCas)
{
  Sentence sentence = selectByAddr(userJCas, Sentence.class,
      aBratAnnotatorModel.getLastSentenceAddress());
  List<Sentence> sentences = JCasUtil.selectCovered(jCas, Sentence.class,
      sentence.getBegin(), sentence.getEnd());
  return sentences.get(0).getAddress();
}

代码示例来源：origin: webanno/webanno

public int getBegin()
{
  return uimaSentence.getBegin();
}

代码示例来源：origin: de.tudarmstadt.ukp.clarin.webanno/webanno-api-annotation

@Override
public void setFirstVisibleUnit(Sentence aFirstVisibleUnit)
{
  JCas jcas;
  try {
    jcas = aFirstVisibleUnit.getCAS().getJCas();
  }
  catch (CASException e) {
    throw new IllegalStateException("Unable to fetch JCas from CAS", e);
  }
  firstVisibleUnitAddress = WebAnnoCasUtil.getAddr(aFirstVisibleUnit);
  firstVisibleUnitBegin = aFirstVisibleUnit.getBegin();
  firstVisibleUnitEnd = aFirstVisibleUnit.getEnd();
  Sentence lastVisibleUnit = getLastSentenceInDisplayWindow(jcas, getAddr(aFirstVisibleUnit),
      getPreferences().getWindowSize());
  firstVisibleUnitIndex = WebAnnoCasUtil.getSentenceNumber(jcas,
      aFirstVisibleUnit.getBegin());
  lastVisibleUnitIndex = WebAnnoCasUtil.getSentenceNumber(jcas, lastVisibleUnit.getBegin());
  unitCount = select(jcas, Sentence.class).size();
  
  windowBeginOffset = aFirstVisibleUnit.getBegin();
  windowEndOffset = lastVisibleUnit.getEnd();
}

代码示例来源：origin: de.tudarmstadt.ukp.dkpro.core/de.tudarmstadt.ukp.dkpro.core.stanfordnlp-gpl

List<CoreMap> sentences = new ArrayList<>();
for (Sentence s : select(aJCas, Sentence.class)) {
  Annotation sentence = new Annotation(s.getCoveredText());
  sentence.set(CharacterOffsetBeginAnnotation.class, s.getBegin());
  sentence.set(CharacterOffsetEndAnnotation.class, s.getEnd());
  sentence.set(SentenceIndexAnnotation.class, sentences.size());

代码示例来源：origin: UKPLab/argument-reasoning-comprehension-task

@Override
  public boolean keepArgument(JCas jCas)
  {
    List<Sentence> sentences = new ArrayList<>(JCasUtil.select(jCas, Sentence.class));

    // remove one-sentence arguments
    if (sentences.size() == 1) {
      return false;
    }

    for (Sentence s : sentences) {
      if (s.getCoveredText().length() > MAX_SENTENCE_LENGTH) {
        return false;
      }
    }

    return true;
  }
}

代码示例来源：origin: oaqa/knn4qa

private void copyAnnotations(JCas jCasSrc, JCas jCasDst) {
  CasCopier   copier = new CasCopier(jCasSrc.getCas(), jCasDst.getCas());

  for (Sentence anSrc : JCasUtil.select(jCasSrc, Sentence.class)) {
   Sentence anDst = (Sentence) copier.copyFs(anSrc);
   anDst.addToIndexes();
  }
  
  for (Token anSrc : JCasUtil.select(jCasSrc, Token.class)) {
   Token anDst = (Token) copier.copyFs(anSrc);
   anDst.addToIndexes();      
  }    
  
  for (POS anSrc : JCasUtil.select(jCasSrc, POS.class)) {
   POS anDst = (POS) copier.copyFs(anSrc);
   anDst.addToIndexes();      
  }    
 }
}

代码示例来源：origin: hltfbk/Excitement-Open-Platform

private Annotation getAnnotationObject(JCas aJCas, String viewName, String type, Integer[] index) throws Exception{
  
  if (type.matches(txpAnn.token))
    return new Token(aJCas.getView(viewName));
  if (type.matches(txpAnn.lemma))
    return new Lemma(aJCas.getView(viewName));
  if (type.matches(txpAnn.pos))
    return getAnnotationObject(aJCas, viewName, txpAnn.getAnnotation(type).get(index), POS.class);
  if (type.matches(txpAnn.sentence))
    return new Sentence(aJCas.getView(viewName));
  if (type.matches(txpAnn.ne))
    return getAnnotationObject(aJCas, viewName, txpAnn.getNEtype(index), NamedEntity.class);
  
  return new Annotation(aJCas.getView(viewName));
}

代码示例来源：origin: de.tudarmstadt.ukp.clarin.webanno/webanno-io-tsv

public int getEnd()
{
  return uimaSentence.getEnd();
}

代码示例来源：origin: de.tudarmstadt.ukp.dkpro.core/de.tudarmstadt.ukp.dkpro.core.io.penntree-asl

private void annotateSentence(JCas aJCas, int aBegin, int aEnd)
{
  new Sentence(aJCas, aBegin, aEnd).addToIndexes();
}

代码示例来源：origin: webanno/webanno

public static void tokenize(JCas aJCas)
{
  BreakIterator bi = BreakIterator.getWordInstance(Locale.US);
  for (Sentence s : select(aJCas, Sentence.class)) {
    bi.setText(s.getCoveredText());
    int last = bi.first();
    int cur = bi.next();
    while (cur != BreakIterator.DONE) {
      int[] span = new int[] { last, cur };
      trim(s.getCoveredText(), span);
      if (!isEmpty(span[0], span[1])) {
        Token seg = new Token(aJCas, span[0] + s.getBegin(), span[1] + s.getBegin());
        seg.addToIndexes(aJCas);
      }
      last = cur;
      cur = bi.next();
    }
  }
}

代码示例来源：origin: de.tudarmstadt.ukp.clarin.webanno/de.tudarmstadt.ukp.clarin.webanno.brat

/**
 * Get the sentence address for jCas from userJCas.
 */
private static int getSentenceAddress(BratAnnotatorModel aBratAnnotatorModel, JCas jCas,
    JCas userJCas)
{
  int sentenceAddress = BratAjaxCasUtil.selectSentenceAt(userJCas,
      aBratAnnotatorModel.getSentenceBeginOffset(),
      aBratAnnotatorModel.getSentenceEndOffset()).getAddress();
  Sentence sentence = selectByAddr(userJCas, Sentence.class, sentenceAddress);
  List<Sentence> sentences = JCasUtil.selectCovered(jCas, Sentence.class,
      sentence.getBegin(), sentence.getEnd());
  return sentences.get(0).getAddress();
}

代码示例来源：origin: de.tudarmstadt.ukp.clarin.webanno/webanno-io-tsv

public int getBegin()
{
  return uimaSentence.getBegin();
}

代码示例来源：origin: hltfbk/Excitement-Open-Platform

/**
 * <B>NOTE:</B> Must be called only after one of the conversion methods was called.
 * @return a mapping between a root, and the text of the tree's sentence. This is an ordered map,
 * ordered by the order of sentences in the text.
 * @throws CasTreeConverterException
 */
public LinkedHashMap<BasicNode, String> getTreesToSentences() throws CasTreeConverterException {
  if (lastRootList == null || lastSentenceList == null) {
    throw new CasTreeConverterException("getTreesToSentences() called before a conversion method was called.");
  }
  if (lastRootList.size() != lastSentenceList.size()) {
    throw new CasTreeConverterException("Internal error - lastRootList(size=" + lastRootList.size() + ") and lastSentenceList(size=" +
                      lastSentenceList.size() + ") are in different sizes.");
  }
  
  LinkedHashMap<BasicNode, String> result = new LinkedHashMap<BasicNode, String>(lastRootList.size());
  Iterator<Sentence> iterSentences = lastSentenceList.iterator();
  for (BasicNode node : lastRootList) {
    Sentence sentence = iterSentences.next();
    result.put(node, sentence.getCoveredText());
  }
  
  return result;
}

内容来源于网络，如有侵权，请联系作者删除！

sentence

相关文章

    查看更多

    热门标签

    更多
    JavaquerypythonNode开发语言requestUtil数据库Table后端算法LoggerMessageElementParser

    最新文章

    更多
    • 蜀ICP备13028337号-1 大数据知识库 https://www.saoniuhuo.com © All rights reserved
    • 本站内容来源互联网,如果侵犯您的权益请联系我们删除, 联系方式：448109455@qq.com