/**
* A dumb vector space model that counts each word's co-occurences with a predefined set of
* content words and uses these co-occurence vectors directly as word representations. The context
* in which a word occurs is the set of content words in an entire sentence.
*
* <p>N.B. Most people would probably not consider this an embedding model, since the words have
* not been embedded in a lower dimensional subspace. However, it is a good starting point.
*
* <p>Since this approach does not share any information between representations of different
* words, we can filter the training data to only include sentences that contain words of
* interest. In other approaches this may not be a good idea.
*
* @param dataPath
* @param targetVocab
* @param contentVocab
* @return
*/
private static HashMap<String, float[]> getEmbeddings(
String dataPath, HashMap<String, Integer> contentVocab, Set<String> targetVocab) {
HashMap<String, float[]> embeddingMatrix = new HashMap<String, float[]>();
for (String target_word : targetVocab) {
embeddingMatrix.put(target_word, new float[contentVocab.size()]);
}
Collection<List<String>> sentenceCollection =
SentenceCollection.Reader.readSentenceCollection(dataPath);
for (List<String> sentence : sentenceCollection) {
Set<String> sw = new HashSet<String>(sentence);
sw.retainAll(targetVocab);
for (String word : sentence) {
if (!contentVocab.containsKey(word)) continue;
int contentWordId = contentVocab.get(word);
for (String targetWord : sw) {
embeddingMatrix.get(targetWord)[contentWordId] =
embeddingMatrix.get(targetWord)[contentWordId] + 1;
}
}
}
return embeddingMatrix;
}
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;
}