train.java

DocAwareIterator jaIter = new DocAwareIterator(myDocData);

AbstractCache<VocabWord> cache = new AbstractCache<>();

TokenizerFactory t = new DefaultTokenizerFactory();
t.setTokenPreProcessor(new CommonPreprocessor());

ParagraphVectors.Builder vecBuilder = new ParagraphVectors.Builder()
				.minWordFrequency(1)
				.iterations(5)
				.epochs(5)
				.layerSize(100)
				.learningRate(0.025)
				.labelsSource(jaIter.getLabelsSource())
				.windowSize(5)
				.iterate(jaIter)
				.trainWordVectors(false)
				.vocabCache(cache)
				.tokenizerFactory(t)
				.sampling(0)
			  .negativeSample(5)
			  .useHierarchicSoftmax(false);

ParagraphVectors vec = vecBuilder.build();

vec.fit();

String modelName = "myModel";
File storedModel = new File("/tmp/", modelName);

WordVectorSerializer.writeParagraphVectors(vec, storedModel);