/**
* 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;
}
/**
* Read the core WordNet senses and map each to a unique integer. Used by the simple model below.
*/
private static HashMap<String, Integer> getWordNetVocab(String coreWordNetPath) throws Exception {
HashMap<String, Integer> vocab = new HashMap<String, Integer>();
BufferedReader reader = new BufferedReader(new FileReader(coreWordNetPath));
String line = "";
while ((line = reader.readLine()) != null) {
String[] parts = line.split(" ");
String word = parts[2].replace("[", "").replace("]", "");
vocab.put(word, vocab.size());
}
reader.close();
return vocab;
}
/**
* Write embeddings to a file.
*
* @param embeddings
* @param embeddingPath
* @param embeddingDim
* @throws Exception
*/
private static void writeEmbeddings(
HashMap<String, float[]> embeddings, String path, int embeddingDim) throws Exception {
BufferedWriter writer = new BufferedWriter(new FileWriter(path));
writer.write(embeddings.size() + " " + embeddingDim + "\n");
for (Map.Entry<String, float[]> wordEmbedding : embeddings.entrySet()) {
String word = wordEmbedding.getKey();
String embeddingString =
Arrays.toString(wordEmbedding.getValue())
.replace(", ", " ")
.replace("[", "")
.replace("]", "");
if (wordEmbedding.getValue().length != embeddingDim) {
System.out.println("The embedding for " + word + " is not " + embeddingDim + "D.");
System.exit(0);
}
writer.write(word + " " + embeddingString + "\n");
}
writer.close();
}
/**
* @author jacqueline
* <p>Take a vocabulary, return a HashMap that maps each word in the vocabulary to a unique
* integer. This integer is the index of the non-zero value in the one-hot vector of size V.
*/
private void encodeVocabulary() {
encodedVocab = new HashMap<String, Integer>();
for (String word : vocabulary) {
encodedVocab.put(word, encodedVocab.size());
}
}