public void ParseEasySentence()
{
// This option shows parsing a list of correctly tokenized words
var sent = new[] { "This", "is", "an", "easy", "sentence", "." };
var rawWords = SentenceUtils.toCoreLabelList(sent);
var parse = _lp.apply(rawWords);
Assert.NotNull(parse);
parse.pennPrint();
// This option shows loading and using an explicit tokenizer
var sent2 = "This is another sentence.";
var tokenizerFactory = PTBTokenizer.factory(new CoreLabelTokenFactory(), "");
using var sent2Reader = new StringReader(sent2);
var rawWords2 = tokenizerFactory.getTokenizer(sent2Reader).tokenize();
parse = _lp.apply(rawWords2);
Assert.NotNull(parse);
var tlp = new PennTreebankLanguagePack();
var gsf = tlp.grammaticalStructureFactory();
var gs = gsf.newGrammaticalStructure(parse);
var tdl = gs.typedDependenciesCCprocessed();
TestContext.Out.WriteLine($"\n{tdl}\n");
var tp = new TreePrint("penn,typedDependenciesCollapsed");
Assert.NotNull(tp);
tp.printTree(parse);
}
public List <string> FindTag(string text, List <string> tag)
{
List <string> adj = new List <string>();
object[] sentences = MaxentTagger.tokenizeText(new java.io.StringReader(text)).toArray();
foreach (ArrayList sentence in sentences)
{
List taggedSentence = this.tagger.tagSentence(sentence);
foreach (CoreLabel word in SentenceUtils.toCoreLabelList(taggedSentence).toArray())
{
if (tag.Contains(word.tag()))
{
adj.Add(word.word());
}
}
}
return(adj);
}
public List <string> FindNouns(string text)
{
List <string> nouns = new List <string>();
object[] sentences = MaxentTagger.tokenizeText(new java.io.StringReader(text)).toArray();
foreach (ArrayList sentence in sentences)
{
List taggedSentence = this.tagger.tagSentence(sentence);
foreach (CoreLabel word in SentenceUtils.toCoreLabelList(taggedSentence).toArray())
{
switch (word.tag())
{
case "NN":
case "NNS":
nouns.Add(word.word());
break;
}
}
}
return(nouns);
}
public List <TargetCandidate> GetAllNounPhrases(string[] sentence, string[] target)
{
var tree = lexParser.apply(SentenceUtils.toCoreLabelList(sentence));
var dependencies = grammaticalStructureFactory.newGrammaticalStructure(tree).typedDependenciesCCprocessed();
List <TargetCandidate> nounPhrases = new List <TargetCandidate>();
var subTrees = tree.subTreeList();
for (int i = 0; i < subTrees.size(); i++)
{
Tree subTree = (Tree)subTrees.get(i);
if (subTree.label().value() == "NP")
{
NounPhrase phrase = NounPhrase.SetSentence(sentence, tree, dependencies, target);
phrase.SetPhrase(SentenceUtils.listToString(subTree.yield()));
nounPhrases.Add(new TargetCandidate(phrase, caching));
}
}
return(nounPhrases);
}
static void Main()
{
// Path to models extracted from `stanford-parser-3.6.0-models.jar`
var jarRoot = @"..\..\..\..\data\paket-files\nlp.stanford.edu\stanford-parser-full-2018-10-17\models\";
var modelsDirectory = jarRoot + @"\edu\stanford\nlp\models";
// Loading english PCFG parser from file
var lp = LexicalizedParser.loadModel(modelsDirectory + @"\lexparser\englishPCFG.ser.gz");
// This sample shows parsing a list of correctly tokenized words
var sent = new[] { "This", "is", "an", "easy", "sentence", "." };
var rawWords = SentenceUtils.toCoreLabelList(sent);
var tree = lp.apply(rawWords);
tree.pennPrint();
// This option shows loading and using an explicit tokenizer
var sent2 = "This is another sentence.";
var tokenizerFactory = PTBTokenizer.factory(new CoreLabelTokenFactory(), "");
var sent2Reader = new StringReader(sent2);
var rawWords2 = tokenizerFactory.getTokenizer(sent2Reader).tokenize();
sent2Reader.close();
var tree2 = lp.apply(rawWords2);
// Extract dependencies from lexical tree
var tlp = new PennTreebankLanguagePack();
var gsf = tlp.grammaticalStructureFactory();
var gs = gsf.newGrammaticalStructure(tree2);
var tdl = gs.typedDependenciesCCprocessed();
Console.WriteLine("\n{0}\n", tdl);
// Extract collapsed dependencies from parsed tree
var tp = new TreePrint("penn,typedDependenciesCollapsed");
tp.printTree(tree2);
}