/**
* 29% in FactorTable.getValue() 28% in CRFCliqueTree.getCalibratedCliqueTree() 12.6% waiting for
* threads
*
* <p>Single threaded: 15000 ms - 26000 ms Multi threaded: 4500 ms - 7000 ms
*
* <p>with 8 cpus, 3.3x - 3.7x speedup, around 800% utilization
*/
public static void benchmarkCRF() {
Properties props = new Properties();
props.setProperty("macro", "true"); // use a generic CRF configuration
props.setProperty("useIfInteger", "true");
props.setProperty("featureFactory", "edu.stanford.nlp.benchmarks.BenchmarkFeatureFactory");
props.setProperty("saveFeatureIndexToDisk", "false");
CRFClassifier<CoreLabel> crf = new CRFClassifier<CoreLabel>(props);
Random r = new Random(42);
List<List<CoreLabel>> data = new ArrayList<>();
for (int i = 0; i < 100; i++) {
List<CoreLabel> sentence = new ArrayList<>();
for (int j = 0; j < 20; j++) {
CoreLabel l = new CoreLabel();
l.setWord("j:" + j);
boolean tag = j % 2 == 0 ^ (r.nextDouble() > 0.7);
l.set(CoreAnnotations.AnswerAnnotation.class, "target:" + tag);
sentence.add(l);
}
data.add(sentence);
}
long msStart = System.currentTimeMillis();
crf.train(data);
long delay = System.currentTimeMillis() - msStart;
System.out.println("Training took " + delay + " ms");
}
private static void taggedLeafLabels(Tree t, List<CoreLabel> l) {
if (t.isPreTerminal()) {
CoreLabel fl = (CoreLabel) t.getChild(0).label();
fl.set(TagLabelAnnotation.class, t.label());
l.add(fl);
} else {
Tree[] kids = t.children();
for (int j = 0, n = kids.length; j < n; j++) {
taggedLeafLabels(kids[j], l);
}
}
}
public static final String doCorefResolution(Annotation annotation) {
Map<Integer, CorefChain> corefs = annotation.get(CorefChainAnnotation.class);
List<CoreMap> sentences = annotation.get(CoreAnnotations.SentencesAnnotation.class);
List<String> resolved = new ArrayList<String>();
for (CoreMap sentence : sentences) {
List<CoreLabel> tokens = sentence.get(CoreAnnotations.TokensAnnotation.class);
for (CoreLabel token : tokens) {
Integer corefClustId = token.get(CorefCoreAnnotations.CorefClusterIdAnnotation.class);
CorefChain chain = corefs.get(corefClustId);
if (chain == null) resolved.add(token.word());
else {
int sentINdx = chain.getRepresentativeMention().sentNum - 1;
CoreMap corefSentence = sentences.get(sentINdx);
List<CoreLabel> corefSentenceTokens = corefSentence.get(TokensAnnotation.class);
CorefMention reprMent = chain.getRepresentativeMention();
if (token.index() < reprMent.startIndex || token.index() > reprMent.endIndex) {
for (int i = reprMent.startIndex; i < reprMent.endIndex; i++) {
CoreLabel matchedLabel = corefSentenceTokens.get(i - 1);
resolved.add(matchedLabel.word());
}
} else resolved.add(token.word());
}
}
}
String resolvedStr = "";
System.out.println();
for (String str : resolved) {
resolvedStr += str + " ";
}
System.out.println(resolvedStr);
return resolvedStr;
}
/**
* Create a mock node, to be added to the dependency tree but which is not part of the original
* sentence.
*
* @param toCopy The CoreLabel to copy from initially.
* @param word The new word to add.
* @param POS The new part of speech to add.
* @return A CoreLabel copying most fields from toCopy, but with a new word and POS tag (as well
* as a new index).
*/
@SuppressWarnings("UnusedDeclaration")
private CoreLabel mockNode(CoreLabel toCopy, String word, String POS) {
CoreLabel mock = new CoreLabel(toCopy);
mock.setWord(word);
mock.setLemma(word);
mock.setValue(word);
mock.setNER("O");
mock.setTag(POS);
mock.setIndex(sentenceLength + 5);
return mock;
}