public static void standfordNLP() {
CoreLabelTokenFactory ctf = new CoreLabelTokenFactory();
PTBTokenizer<CoreLabel> ptb =
new PTBTokenizer<>(new StringReader(paragraph), ctf, "invertible=true");
while (ptb.hasNext()) {
CoreLabel cl = ptb.next();
System.out.print(
cl.originalText() + " [" + cl.beginPosition() + "-" + cl.endPosition() + "];");
}
System.out.println();
}
public static void resolveAnaphora(String text) {
RedwoodConfiguration.empty().capture(System.err).apply();
Annotation document = new Annotation(text);
Properties props = new Properties();
props.put("annotators", "tokenize, ssplit, pos, lemma, ner, parse, dcoref");
props.put("dcoref.female", "female.unigram.txt");
props.put("dcoref.male", "male.unigram.txt");
StanfordCoreNLP pipeline = new StanfordCoreNLP(props);
pipeline.annotate(document);
RedwoodConfiguration.current().clear().apply();
Map<Integer, CorefChain> graph = document.get(CorefChainAnnotation.class);
List<CoreMap> stnfrdSentences = document.get(SentencesAnnotation.class);
ImmutableMultimap.Builder<Integer, Pair<CorefChain, CorefMention>> records =
ImmutableMultimap.builder();
ImmutableMultimap.Builder<Integer, Pair<CorefChain, CorefMention>> recordsOrdered =
ImmutableMultimap.builder();
graph.forEach(
(key, value) -> {
value
.getMentionMap()
.forEach(
(intPair, corefSet) -> {
corefSet.forEach(
mention -> records.put(mention.sentNum, Pair.of(value, mention)));
});
});
recordsOrdered =
records.orderKeysBy(
new Comparator<Integer>() {
@Override
public int compare(Integer o1, Integer o2) {
return o1 - o2;
}
});
recordsOrdered
.build()
.asMap()
.forEach(
(sentNum, mentionList) -> {
CoreMap sentence = stnfrdSentences.get(sentNum - 1);
List<CoreLabel> stnfrdtokens = sentence.get(TokensAnnotation.class);
mentionList.forEach(
pair -> {
CorefChain chain = pair.getLeft();
CorefMention mention = pair.getRight();
String root = chain.getRepresentativeMention().mentionSpan;
if (!mention.mentionSpan.equalsIgnoreCase(root)
&& (!root.contains(mention.mentionSpan)
&& !mention.mentionSpan.contains(root))
&& (!replacementList.contains(root.toLowerCase()))
&& (root.split("\\s").length < 3)
&& (replacementList.contains(mention.mentionSpan.toLowerCase()))) {
if (mention.mentionSpan.equalsIgnoreCase("her")
|| mention.mentionSpan.equalsIgnoreCase("his")) {
root += "'s";
}
stnfrdtokens.get(mention.startIndex - 1).setOriginalText(root);
}
});
String sent = "";
for (CoreLabel token : stnfrdtokens) {
sent += token.originalText() + " ";
}
;
resolvedSentences += sent + "\n";
});
}
/** ************************************************************ */
private boolean needSpaceBefore(CoreLabel label) {
return needSpaceBefore(label.originalText());
}