public static ProcessedEntity Classify(this StanfordCoreNLP nlp, string source)
{
CoreDocument document = new CoreDocument(source);
nlp.annotate(document);
return(document.sentences()
.toArray()
.OfType <CoreSentence>()
.Select(s => new ParsedSentence(s))
.Aggregate(new ProcessedEntity(), (r, s) => ProcessedEntity.Union(r, s.ToProcessedEntity())));
}
private static void ExtractNouns(CoreDocument coredoc, Lucene.Net.Documents.Document document)
{
List <string> nouns = new List <string>();
for (int i = 0; i < coredoc.sentences().size(); i++)
{
CoreSentence sent = (CoreSentence)coredoc.sentences().get(i);
for (int j = 0; j < sent.tokens().size(); j++)
{
// Condition: if the word is a noun (posTag starts with "NN")
if (sent.posTags() != null && sent.posTags().get(j) != null)
{
string posTags = sent.posTags().get(j).ToString();
if (posTags.Contains("NN"))
{
var noun = sent.tokens().get(j).ToString();
noun = noun.Remove(noun.Length - 2);
nouns.Add(noun);
}
}
}
}
NounPhrases.Add(document.GetField("id").GetInt32Value().Value, nouns);
}