private Set<Integer> negativeSampleContexts(int wordIndex) {
Set<Integer> negativeContexts = new HashSet<Integer>();
Set<Integer> positiveContexts = contextPairs.get(wordIndex);
while (negativeContexts.size() < kSamples) {
int contextIndex = (int) (Math.random() * V);
if (!positiveContexts.contains(contextIndex) && negativeContexts.contains(contextIndex)) {
negativeContexts.add(contextIndex);
}
}
return negativeContexts;
}
/**
* @author jacqueline If boolean sampleUnigram = true, we use noiseSampler from
* randomContextGeneration to model the unigram probability distribution raised to specfied
* power, default 3/4. Otherwise, use overloaded negativeSampleContexts(int wordIndex)
* method to draw from uniform probability distribution.
*/
private Set<Integer> negativeSampleContexts(
int wordIndex, EnumeratedDistribution<String> weightedRandomSample) {
Set<Integer> negativeContexts = new HashSet<Integer>();
Set<Integer> positiveContexts = contextPairs.get(wordIndex);
while (negativeContexts.size() < kSamples) {
String possibleContext = weightedRandomSample.sample();
int contextIndex = encodedVocab.get(possibleContext);
if (!positiveContexts.contains(contextIndex) && !negativeContexts.contains(contextIndex)) {
negativeContexts.add(contextIndex);
}
}
return negativeContexts;
}
