本文整理了Java中edu.illinois.cs.cogcomp.core.datastructures.textannotation.TextAnnotation
类的一些代码示例,展示了TextAnnotation
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。TextAnnotation
类的具体详情如下:
包路径:edu.illinois.cs.cogcomp.core.datastructures.textannotation.TextAnnotation
类名称:TextAnnotation
[英]This class contains all annotation for a single piece of text (which could contain more than one sentence.)
[中]此类包含单个文本(可能包含多个句子)的所有注释
代码示例来源:origin: CogComp/cogcomp-nlp
public void addView(TextAnnotation ta, boolean overwrite) {
TextAnnotation newTA = null;
try {
newTA = annotate(ta.getText(), overwrite);
} catch (Exception e) {
e.printStackTrace();
}
for (String vu : viewsToAdd) {
ta.addView(vu, newTA.getView(vu));
}
}
代码示例来源:origin: CogComp/cogcomp-nlp
@Override
public void addView(TextAnnotation ta) throws AnnotatorException {
assert (ta.hasView(ViewNames.SENTENCE));
SpanLabelView quantifierView =
new SpanLabelView(ViewNames.QUANTITIES, "illinois-quantifier", ta, 1d);
List<QuantSpan> quantSpans = getSpans(ta.getTokenizedText(), true, ta);
for (QuantSpan span : quantSpans) {
int startToken = ta.getTokenIdFromCharacterOffset(span.start);
int endToken = ta.getTokenIdFromCharacterOffset(span.end);
quantifierView.addSpanLabel(startToken, endToken, span.object.toString(), 1d);
}
ta.addView(ViewNames.QUANTITIES, quantifierView);
}
代码示例来源:origin: CogComp/cogcomp-nlp
static public void printTextAnnotation(PrintStream out, TextAnnotation ta) {
out.println("TextAnnotation with id: " + ta.getId());
String rawText = ta.getText();
out.println("Raw Text: " + rawText);
out.println(getLineFill());
out.println("TextAnnotation Views:");
for (String name : ta.getAvailableViews()) {
out.println("View Name: " + name);
out.println(ta.getView(name).toString());
out.println(getLineFill());
}
}
代码示例来源:origin: CogComp/cogcomp-nlp
/**
* Gets the sentence containing the specified token
*/
public Sentence getSentenceFromToken(int tokenId) {
return this.getSentence(this.getSentenceId(tokenId));
}
代码示例来源:origin: edu.illinois.cs.cogcomp/illinois-comma
public String getWordToRight(int distance) {
// Dummy symbol for sentence end (in case comma is the second to last word in the sentence)
if (commaPosition + distance >= s.ta.getTokens().length)
return "###";
return s.ta.getToken(commaPosition + distance);
}
代码示例来源:origin: edu.illinois.cs.cogcomp/illinois-edison
private static String getSafeToken(TextAnnotation ta, int wordPosition) {
String token = "*";
if (wordPosition >= 0 && wordPosition < ta.size())
token = ta.getToken(wordPosition);
return token;
}
代码示例来源:origin: CogComp/cogcomp-nlp
@Override
public void addView(TextAnnotation ta) {
TokenLabelView posView = new TokenLabelView(ViewNames.POS, "ParsePOS", ta, 1.0);
int tokenId = 0;
for (int sentenceId = 0; sentenceId < ta.getNumberOfSentences(); sentenceId++) {
Tree<String> parseTree = ((TreeView) (ta.getView(parseViewName))).getTree(sentenceId);
parseTree = ParseUtils.snipNullNodes(parseTree);
parseTree = ParseUtils.stripFunctionTags(parseTree);
if (parseTree.getYield().size() != ta.getSentence(sentenceId).size())
throw new IllegalStateException("Parse tree size != ta.size()");
for (Tree<String> y : parseTree.getYield()) {
posView.addTokenLabel(tokenId++, y.getParent().getLabel(), 1.0);
}
}
ta.addView(getViewName(), posView);
}
代码示例来源:origin: edu.illinois.cs.cogcomp/saul-examples
private void addView(TextAnnotation ta, List<String> labels) {
TokenLabelView labelView = new TokenLabelView(viewName, ta);
List constituents = ta.getView(ViewNames.TOKENS).getConstituents();
assert constituents.size() == labels.size();
for (int i = 0; i < constituents.size(); ++i) {
Constituent constituent = (Constituent) constituents.get(i);
labelView.addTokenLabel(constituent.getStartSpan(), labels.get(i), 1.0D);
}
ta.addView(viewName, labelView);
}
代码示例来源:origin: edu.illinois.cs.cogcomp/illinois-depparse
TextAnnotation annotate(String corpusId, String sentId, String[] tokens)
throws AnnotatorException {
// Ignore the root token
List<String[]> words =
Collections.singletonList(Arrays.copyOfRange(tokens, 1, tokens.length));
TextAnnotation ta =
BasicTextAnnotationBuilder.createTextAnnotationFromTokens(corpusId, sentId, words);
ta.addView(pos);
ta.addView(lemma);
ta.addView(chunk);
return ta;
}
代码示例来源:origin: CogComp/cogcomp-nlp
public String getPOSToLeft(int distance) {
TokenLabelView posView;
if (GOLD)
posView = (TokenLabelView) s.goldTa.getView(ViewNames.POS);
else
posView = (TokenLabelView) s.ta.getView(ViewNames.POS);
String pos = posView.getLabel(commaPosition - distance);
if (pos.equals("DT") && distance == 1 && getWordToRight(distance).equalsIgnoreCase("the"))
return "DT-the";
else
return pos;
}
代码示例来源:origin: edu.illinois.cs.cogcomp/illinois-edison
@Override
public void addView(TextAnnotation input) {
TokenLabelView view = new TokenLabelView(getViewName(), "PorterStemmer", input, 1.0);
synchronized (instance) {
for (int i = 0; i < input.size(); i++) {
stemmer.setCurrent(input.getToken(i));
stemmer.stem();
view.addTokenLabel(i, stemmer.getCurrent(), 1.0);
}
}
input.addView(getViewName(), view);
}
代码示例来源:origin: CogComp/cogcomp-nlp
public static String printTextAnnotation(TextAnnotation ta ) throws IOException
{
StringBuilder bldr = new StringBuilder();
bldr.append( "TextAnnotation for text: " );
bldr.append( ta.getText() );
for ( String vName: ta.getAvailableViews() ) {
bldr.append(printView( ta.getView( vName )));
}
return bldr.toString();
}
代码示例来源:origin: edu.illinois.cs.cogcomp/illinois-srl
private void addViews(TextAnnotation ta) throws AnnotatorException {
for (String view : requiredViews) {
if (!ta.hasView(view))
annotator.addView(ta, view);
}
if (!ta.hasView(ViewNames.CLAUSES_STANFORD))
ta.addView(ClauseViewGenerator.STANFORD);
if (!ta.hasView(ViewNames.DEPENDENCY + ":" + ViewNames.PARSE_STANFORD))
ta.addView(new HeadFinderDependencyViewGenerator(ViewNames.PARSE_STANFORD));
}
}
代码示例来源:origin: edu.illinois.cs.cogcomp/illinois-srl
private void addPredicateArgs(List<String[]> columns, TextAnnotation ta) {
PredicateArgumentView predArgView = null;
if (ta.hasView(predicateArgumentViewName))
predArgView = (PredicateArgumentView) ta.getView(predicateArgumentViewName);
convertPredicateArgView(ta, predArgView, columns, true);
}
代码示例来源:origin: CogComp/cogcomp-nlp
@Override
public boolean hasView(String viewName) {
return this.textAnnotation.hasView(viewName);
}
代码示例来源:origin: CogComp/cogcomp-nlp
public Constituent getChunkToRightOfComma(int distance) {
// We don't have gold SHALLOW_PARSE
SpanLabelView chunkView = (SpanLabelView) s.ta.getView(ViewNames.SHALLOW_PARSE);
List<Constituent> chunksToRight =
chunkView.getSpanLabels(commaPosition + 1, s.ta.getTokens().length);
Collections.sort(chunksToRight, TextAnnotationUtilities.constituentStartComparator);
Constituent chunk;
if (distance <= 0 || distance > chunksToRight.size())
chunk = null;
else
chunk = chunksToRight.get(distance - 1);
return chunk;
}
代码示例来源:origin: CogComp/cogcomp-nlp
/**
* given a {@link TextAnnotation} for a sentence with annotations, map its annotations into a
* TextAnnotation object for a longer text containing that sentence.
* @param sentenceTa annotated TextAnnotation for sentence
* @param textTa TextAnnotation for longer text containing sentence, without annotations for that sentence
* @param sentenceId index of the sentence in the longer text
*/
static public void mapSentenceAnnotationsToText(TextAnnotation sentenceTa, TextAnnotation textTa, int sentenceId ) {
assert(sentenceId < textTa.getNumberOfSentences());
assert(sentenceTa.getText().equals(textTa.getSentence(sentenceId).getText()));
int start = textTa.getSentence(sentenceId).getStartSpan();
int end = textTa.getSentence(sentenceId).getEndSpan();
copyViewsFromTo(sentenceTa, textTa, start, end, start);
}
代码示例来源:origin: CogComp/cogcomp-nlp
/**
* create a Lemma view in the TextAnnotation argument, and return a reference to that View.
*/
public View createLemmaView(TextAnnotation inputTa) throws IOException {
String[] toks = inputTa.getTokens();
TokenLabelView lemmaView = new TokenLabelView(ViewNames.LEMMA, NAME, inputTa, 1.0);
for (int i = 0; i < toks.length; ++i) {
String lemma = getLemma(inputTa, i);
Constituent lemmaConstituent =
new Constituent(lemma, ViewNames.LEMMA, inputTa, i, i + 1);
lemmaView.addConstituent(lemmaConstituent);
}
inputTa.addView(ViewNames.LEMMA, lemmaView);
return lemmaView;
}
代码示例来源:origin: CogComp/cogcomp-nlp
public String getCommaID() {
return commaPosition + " " + s.goldTa.getId();
}
代码示例来源:origin: CogComp/cogcomp-nlp
public static void main(String[] args) {
TextAnnotationBuilder tokenizer = MultiLingualTokenizer.getTokenizer("ja");
String text = "\"ペンシルベニアドイツ語\",\"text\":\"ペンシルベニアドイツ語(標準ドイ"
+ "ツ語:Pennsylvania-Dutch, Pennsilfaani-Deitsch、アレマン語:Pennsylvania-Ditsch、英語:Pennsylvania-German)"
+ "は、北アメリカのカナダおよびアメリカ中西部でおよそ15万から25万人の人びとに話されているドイツ語の系統である。高地ドイツ語の"
+ "うち上部ドイツ語の一派アレマン語の一方言である。ペンシルベニアアレマン語(Pennsilfaani-Alemanisch, Pennsylvania-Alemannic)"
+ "とも呼ばれる。";
TextAnnotation ta = tokenizer.createTextAnnotation(text);
for(int i = 0; i < ta.getNumberOfSentences(); i++)
System.out.println(ta.getSentence(i).getTokenizedText());
}
}
内容来源于网络,如有侵权,请联系作者删除!