/// <summary>
/// Setup extended tagger that includes POS, lemma and entity analysis
/// </summary>
private void SetupExtendedTagger()
{
PerformanceTester.StartMET("NLP");
// Get path to Stanford NLP models
var jarRoot = Path.Combine(Utility.GetResourcesFolder(), @"stanford-corenlp-3.9.2-models");
// Turn off logging
RedwoodConfiguration.current().clear().apply();
var props = new java.util.Properties();
props.setProperty("annotators", "tokenize, ssplit, pos, lemma, ner");
// Makes Named Entity Recognition work in the library
props.setProperty("ner.useSUTime", "0");
props.put("ner.applyFineGrained", "0");
props.put("ner.fine.regexner.mapping", jarRoot + @"\edu\stanford\nlp\models\kbp\english\");
// Set current directory
var curDir = Environment.CurrentDirectory;
var modelsDirectory = curDir + "\\" + jarRoot + @"\edu\stanford\nlp\models";
Directory.SetCurrentDirectory(jarRoot);
// Load Stanford NLP
Tagger = new StanfordCoreNLP(props);
PerformanceTester.StopMET("NLP");
}
public static void Demonstrate(string text, POSMode partOfSpeechMode, NERMode namedEntityRecognitionMode, bool disableLogging = true)
{
if (disableLogging)
{
RedwoodConfiguration.current().clear().apply();
}
//Input
//Console.WriteLine("Input: {0}\n\n\n", text);
////Tokenization
//Console.WriteLine("Tokenization:");
//Tokenisation.TokenizeText(text);
//Console.WriteLine("\n\n\n");
////POS
//Console.WriteLine("Part Of Speech:");
//PartOfSpeech.Tag(text, partOfSpeechMode);
//Console.WriteLine("\n\n\n");
////NER
//Console.WriteLine("Named Entity Recognition:");
//var ner = new NER(namedEntityRecognitionMode);
//Console.WriteLine(ner.classifyToString(text));
//Console.WriteLine("\n\n\n");
////Parser
//Console.WriteLine("Parsed Text:");
//Parser.ParseString(text);
//Console.WriteLine("\n\n\n");
//Find co-reference
CorefAnnotator.FindCoreferenceResolution(text);
}
public static void Execute(string option, string text, bool disableLogging = true)
{
if (disableLogging)
{
RedwoodConfiguration.current().clear().apply();
}
var jarRoot = @"../../../data/paket-files/stanford-corenlp-3.9.1-models/";
var props = new Properties();
props.setProperty("annotators", option);
props.setProperty("ner.useSUTime", "0");
// We should change current directory, so StanfordCoreNLP could find all the model files automatically
var curDir = Environment.CurrentDirectory;
Directory.SetCurrentDirectory(jarRoot);
var pipeline = new StanfordNLP.StanfordCoreNLP(props);
Directory.SetCurrentDirectory(curDir);
// Annotation
var annotation = new StanfordNLP.Annotation(text);
pipeline.annotate(annotation);
//get sentencesAnnotation to get sentences
var sentencesAnnotation = new CoreAnnotations.SentencesAnnotation().getClass();
//get tokensAnnotaion to get tokens in each sentence
var tokensAnnotaion = new CoreAnnotations.TokensAnnotation().getClass();
//get posAnnotation to get POS result of each token
var posAnnotation = new CoreAnnotations.PartOfSpeechAnnotation().getClass();
//get nerAnnotation to get NER result of each token
var nerAnnotaion = new CoreAnnotations.NamedEntityTagAnnotation().getClass();
var deparseAnnotation = new TreeCoreAnnotations.TreeAnnotation().getClass();
//deparseAnnotation = new TypedDependency().getClass();
var sentences = annotation.get(sentencesAnnotation) as ArrayList;
foreach (CoreMap sentence in sentences.toArray())
{
var tokens = (ArrayList)sentence.get(tokensAnnotaion);
Console.WriteLine("Token-POS-NER: ");
foreach (CoreLabel token in tokens)
{
Console.Write($"{token.value()}-{token.get(posAnnotation)}-{token.get(nerAnnotaion)} ");
}
Console.WriteLine("\n\n\n");
var parsedText = (Tree)sentence.get(deparseAnnotation);
if (parsedText != null)
{
Console.WriteLine("Parsed Text: ");
new TreePrint("penn,typedDependenciesCollapsed").printTree(parsedText);
}
}
}
//*************************************************/
// METHODS
//*************************************************/
#region Methods
/// <summary>
/// Setup tagger including POS
/// </summary>
private void SetupTagger()
{
PerformanceTester.StartMET("NLP");
// Get path to Stanford NLP models
var jarRoot = Path.Combine(Utility.GetResourcesFolder(), @"stanford-corenlp-3.9.2-models");
// Turn off logging
RedwoodConfiguration.current().clear().apply();
// Set properties
var props = new java.util.Properties();
props.setProperty("annotators", "tokenize, ssplit, pos");
// Set current directory
var curDir = Environment.CurrentDirectory;
var modelsDirectory = curDir + "\\" + jarRoot + @"\edu\stanford\nlp\models";
Directory.SetCurrentDirectory(jarRoot);
// Load Stanford NLP
Tagger = new StanfordCoreNLP(props);
PerformanceTester.StopMET("NLP");
}