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;
}
public WordSim(
String dataPath,
int kSamples,
int dimensions,
int contextSize,
double power,
double alpha,
double min_eta,
double sigma,
int epochs,
boolean skipGram,
boolean negativeSampling,
boolean sampleUnigram,
double learningDecay) {
this.sentenceCollection = SentenceCollection.Reader.readSentenceCollection(dataPath);
this.kSamples = kSamples;
this.dimensions = dimensions;
this.contextSize = contextSize;
this.power = power;
this.alpha = alpha;
this.min_eta = min_eta;
this.sigma = sigma;
this.epochs = epochs;
this.skipGram = skipGram;
this.negativeSampling = negativeSampling;
this.sampleUnigram = sampleUnigram;
this.learningDecay = learningDecay;
this.vocabulary = LanguageModelTester.extractVocabulary(sentenceCollection);
encodeVocabulary(); // create one-hot encoding index for all words in vocabulary
this.V = vocabulary.size(); // cardinality of vocabulary
setAllContexts(); // create HashMap for all observed positive contexts for each word
if (sampleUnigram)
randomContextGeneration(); // create weighted random sampler for noise distribution
else noiseSampler = null;
}