public static ArrayList<String[]> extractNounPhrases(
StanfordCoreNLP pipeline, String text, int searchRange) {
ArrayList<String[]> wordPairs = new ArrayList<String[]>();
Annotation document = new Annotation(text);
pipeline.annotate(document);
List<CoreMap> sentences = document.get(SentencesAnnotation.class);
MAX_STEPS = searchRange;
for (CoreMap sentence : sentences) {
List<CoreLabel> labels = sentence.get(TokensAnnotation.class);
// Check negation
boolean hasNegation = false;
for (CoreLabel label : labels) {
if (NEGATIONS.contains(label.lemma().toLowerCase())) {
hasNegation = true;
}
}
for (int idx = 0; idx < labels.size(); idx++) {
CoreLabel label = labels.get(idx);
if (NN_TAGS.contains(label.get(PartOfSpeechAnnotation.class))) {
for (int step = 1; step <= MAX_STEPS; step++) {
CoreLabel leftLabel = labels.get(Math.max(0, idx - step));
if (JJ_TAGS.contains(leftLabel.tag())) {
if (hasNegation)
addPair(
wordPairs,
NOT_PREFIX + leftLabel.get(LemmaAnnotation.class),
label.get(LemmaAnnotation.class));
else
addPair(
wordPairs,
leftLabel.get(LemmaAnnotation.class),
label.get(LemmaAnnotation.class));
break;
}
CoreLabel rightLabel = labels.get(Math.min(idx + step, labels.size() - 1));
if (JJ_TAGS.contains(rightLabel.tag())) {
if (hasNegation)
addPair(
wordPairs,
NOT_PREFIX + rightLabel.get(LemmaAnnotation.class),
label.get(LemmaAnnotation.class));
else
addPair(
wordPairs,
rightLabel.get(LemmaAnnotation.class),
label.get(LemmaAnnotation.class));
break;
}
}
}
}
}
return wordPairs;
}
public String[] wordsSegment(String text) {
String[] listTokenSens = null;
List<String> listSens = new ArrayList<String>();
// creates a StanfordCoreNLP object, with POS tagging, lemmatization,
// NER, parsing, and coreference resolution
Properties props = new Properties();
props.put("annotators", "tokenize, ssplit");
StanfordCoreNLP pipeline = new StanfordCoreNLP(props);
// create an empty Annotation just with the given text
Annotation document = new Annotation(text);
// run all Annotators on this text
pipeline.annotate(document);
// these are all the sentences in this document
// a CoreMap is essentially a Map that uses class objects as keys and
// has values with custom types
List<CoreMap> sentences = document.get(SentencesAnnotation.class);
for (CoreMap sentence : sentences) {
// traversing the words in the current sentence
// a CoreLabel is a CoreMap with additional token-specific methods
List<String> listWord = new ArrayList<String>();
for (CoreLabel token : sentence.get(TokensAnnotation.class)) {
System.err.println(token.lemma());
// this is the text of the token
String word = token.get(TextAnnotation.class);
listWord.add(word);
// this is the POS tag of the token
// String pos = token.get(PartOfSpeechAnnotation.class);
}
listSens.add(StringUtils.join(listWord, " "));
}
listTokenSens = new String[listSens.size()];
listTokenSens = listSens.toArray(listTokenSens);
return listTokenSens;
}
public void process(String inFilepath, String outFilepath, String nerOutFile) {
try {
StringBuilder inText = new StringBuilder();
StringBuilder outText = new StringBuilder();
StringBuilder nerText = new StringBuilder();
// read some text in the inText variable from input file
BufferedReader reader = new BufferedReader(new FileReader(inFilepath));
String line = null;
while ((line = reader.readLine()) != null) {
if (line.trim().length() == 0) continue;
inText.append(line + "\n");
}
reader.close();
// create an empty Annotation just with the given text
Annotation document = new Annotation(inText.toString());
// run all Annotators on this text
pipeline.annotate(document);
// these are all the sentences in this document
// a CoreMap is essentially a Map that uses class objects as keys and has values with custom
// types
List<CoreMap> sentences = document.get(SentencesAnnotation.class);
for (CoreMap sentence : sentences) {
// traversing the words in the current sentence
// a CoreLabel is a CoreMap with additional token-specific methods
for (CoreLabel token : sentence.get(TokensAnnotation.class)) {
totalWords++;
String pos = token.tag();
if (tagFilter.contains(pos)) {
remainWords++;
String lemma = token.lemma();
outText.append(lemma + " ");
if (nerFilter.contains(token.ner())) {
nerText.append(token.word() + " ");
}
}
}
}
// write the processed text to output file
FileWriter fw = FileUtil.open(outFilepath);
fw.append(outText);
FileUtil.close(fw);
if (nerOutFile != null) {
FileWriter fw2 = FileUtil.open(nerOutFile);
fw2.append(nerText);
FileUtil.close(fw2);
}
} catch (FileNotFoundException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}