String textWithDots = text.replaceAll("\\n\\n", ".\n");
text = removeNonUtf8CompliantCharacters(text);
SentenceDetectorME sentenceDetector = new SentenceDetectorME(getSentenceModel("en"));
Span[] sentenceSpans = sentenceDetector.sentPosDetect(textWithDots);
NameFinderME finder = new NameFinderME(nameFinderModel);
Tokenizer tokenizer = openNLP.getTokenizer(language);
Map<String,List<NameOccurrence>> nameOccurrences = new LinkedHashMap<String,List<NameOccurrence>>();
for (int i = 0; i < sentenceSpans.length; i++) {