static void Main()
{
// Path to models extracted from `stanford-parser-3.6.0-models.jar`
var jarRoot = @"..\..\..\..\paket-files\nlp.stanford.edu\stanford-parser-full-2016-10-31\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);
}
public static void DemoAPI(LexicalizedParser lp)
{
// This option shows parsing a list of correctly tokenized words
var sent = new[] { "This", "is", "an", "easy", "sentence", "." };
java.util.List rawWords = Sentence.toCoreLabelList(sent);
Tree parse = lp.apply(rawWords);
parse.pennPrint();
// This option shows loading and using an explicit tokenizer
const string Sent2 = "This is another sentence.";
TokenizerFactory tokenizerFactory = PTBTokenizer.factory(new CoreLabelTokenFactory(), "");
var sent2Reader = new StringReader(Sent2);
java.util.List rawWords2 = tokenizerFactory.getTokenizer(sent2Reader).tokenize();
parse = lp.apply(rawWords2);
var tlp = new PennTreebankLanguagePack();
GrammaticalStructureFactory gsf = tlp.grammaticalStructureFactory();
GrammaticalStructure gs = gsf.newGrammaticalStructure(parse);
java.util.List tdl = gs.typedDependenciesCCprocessed();
Console.WriteLine("\n{0}\n", tdl);
var tp = new TreePrint("penn,typedDependenciesCollapsed");
tp.printTree(parse);
}
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 void ProcessText(string inputText)
{
var jarRoot = "C:\\stanford-parser-full-2016-10-31\\stanford-parser-3.7.0-models";//\\edu\\stanford\\nlp\\models";//"nlp.stanford.edu\\stanford-parser-full-2017-06-09\\models";
var modelsDirectory = jarRoot + "\\edu\\stanford\\nlp\\models";
// Loading english PCFG parser from file
var lp = LexicalizedParser.loadModel(modelsDirectory + "\\lexparser\\englishPCFG.ser.gz");
// This option shows loading and using an explicit tokenizer
var tokenizerFactory = PTBTokenizer.factory(new CoreLabelTokenFactory(), "");
var sentReader = new StringReader(inputText);
var rawWords = tokenizerFactory.getTokenizer(sentReader).tokenize();
sentReader.close();
var tree = lp.apply(rawWords);
//Extract dependencies from lexical tree
var tlp = new PennTreebankLanguagePack();
var gsf = tlp.grammaticalStructureFactory();
var gs = gsf.newGrammaticalStructure(tree);
var tdl = gs.typedDependenciesCCprocessed();
Console.WriteLine("\n{0}\n", tdl);
// Extract collapsed dependencies from parsed tree
var tp = new TreePrint("penn,typedDependenciesCollapsed");
tp.printTree(tree);
}
public static void ParseString(string sentence)
{
// Path to models extracted from `stanford-parser-3.6.0-models.jar`
var modelsDirectory = @"../../../data/paket-files/stanford-corenlp-3.9.1-models/edu/stanford/nlp/models";
var model = @"/lexparser/englishPCFG.ser.gz";
//var model = @"/parser/nndep/english_SD.gz";
// Loading english PCFG parser from file
var lp = LexicalizedParser.loadModel(modelsDirectory + model);
// This sample shows parsing a list of correctly tokenized words
//var rawWords = SentenceUtils.toCoreLabelList(sentence);
//var tree = lp.apply(rawWords);
//tree.pennPrint();
// This option shows loading and using an explicit tokenizer
var tokenizerFactory = PTBTokenizer.factory(new CoreLabelTokenFactory(), "");
var sent2Reader = new StringReader(sentence);
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);
}
public ParsedStatementFactory.ParseResult ParseStatement(string input)
{
var sent2Reader = new StringReader(input);
var rawWords2 = _tokenizerFactory.getTokenizer(sent2Reader).tokenize();
var parse = _lp.apply(rawWords2);
var gs = _structureFactory.newGrammaticalStructure(parse);
var tdl = gs.typedDependenciesCCprocessed();
//System.Console.WriteLine("newGrammaticalStructure:\n{0}\n", gs);
//System.Console.WriteLine("typedDependenciesCCprocessed:\n{0}\n", tdl);
//var tp = new TreePrint("penn,typedDependenciesCollapsed");
//tp.printTree(parse);
//return new ParsedStatement(parse);
var xmlTreePrint = new TreePrint("xmlTree, dependencies", "xml, collapsedDependencies", _tlp);
var stream = new ByteArrayOutputStream();
xmlTreePrint.printTree(parse, new PrintWriter(stream));
string xmlOutput = stream.toString() + "</s>";
//System.Console.WriteLine("xml:\n{0}\n", xmlOutput);
return(ParsedStatementFactory.CreateParsedStatement(xmlOutput));
//System.Console.WriteLine("TreePrint: \n{0}\n", parse);
}
//use Stanford.NLP.Net to parse the sentence
static Tree Parse(string sent)
{
// Loading english PCFG parser from file
var lp = LexicalizedParser.loadModel(modelsDirectory + "\\lexparser\\englishPCFG.ser.gz");
var tokenizerFactory = PTBTokenizer.factory(new CoreLabelTokenFactory(), "");
var sentReader = new java.io.StringReader(sent);
var rawWords = tokenizerFactory.getTokenizer(sentReader).tokenize();
sentReader.close();
var tree = lp.apply(rawWords);
// Extract dependencies from lexical tree
var tlp = new PennTreebankLanguagePack();
var gsf = tlp.grammaticalStructureFactory();
var gs = gsf.newGrammaticalStructure(tree);
var tdl = gs.typedDependenciesCCprocessed();
// Extract collapsed dependencies from parsed tree
//var tp = new TreePrint("penn,typedDependenciesCollapsed");
var tp = new TreePrint("penn");
tp.printTree(tree);
return(tree);
}
public ParsedStatement ParseSentence(string input)
{
var sent2Reader = new StringReader(input);
var rawWords2 = _tokenizerFactory.getTokenizer(sent2Reader).tokenize();
var parse = _lp.apply(rawWords2);
var gs = _structureFactory.newGrammaticalStructure(parse);
var tdl = gs.typedDependenciesCCprocessed();
System.Console.WriteLine("\n{0}\n", tdl);
var tp = new TreePrint("penn,typedDependenciesCollapsed");
tp.printTree(parse);
return(new ParsedStatement(parse));
//System.Console.WriteLine("TreePrint: \n{0}\n", parse);
}
static void Main()
{
// Path to models extracted from `stanford-parser-3.6.0-models.jar`
var jarRoot = @"..\..\..\..\paket-files\nlp.stanford.edu\stanford-parser-full-2015-12-09\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 = Sentence.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);
}
//use Stanford.NLP.Net to parse the sentence
Tree Parse(string sent)
{
var tokenizerFactory = PTBTokenizer.factory(new CoreLabelTokenFactory(), "");
var sentReader = new java.io.StringReader(sent);
var rawWords = tokenizerFactory.getTokenizer(sentReader).tokenize();
sentReader.close();
var tree = lp.apply(rawWords);
// Extract dependencies from lexical tree
var tlp = new PennTreebankLanguagePack();
var gsf = tlp.grammaticalStructureFactory();
var gs = gsf.newGrammaticalStructure(tree);
var tdl = gs.typedDependenciesCCprocessed();
// Extract collapsed dependencies from parsed tree
//var tp = new TreePrint("penn,typedDependenciesCollapsed");
var tp = new TreePrint("penn");
tp.printTree(tree);
return(tree);
}
public static void DemoAPI(LexicalizedParser lp)
{
// This option shows parsing a list of correctly tokenized words
var sent = new[] { "This", "is", "an", "easy", "sentence", "." };
var rawWords = Sentence.toCoreLabelList(sent);
var parse = lp.apply(rawWords);
parse.pennPrint();
// This option shows loading and using an explicit tokenizer
const string Sent2 = "This is another sentence.";
var tokenizerFactory = PTBTokenizer.factory(new CoreLabelTokenFactory(), "");
var sent2Reader = new StringReader(Sent2);
var rawWords2 = tokenizerFactory.getTokenizer(sent2Reader).tokenize();
parse = lp.apply(rawWords2);
var tlp = new PennTreebankLanguagePack();
var gsf = tlp.grammaticalStructureFactory();
var gs = gsf.newGrammaticalStructure(parse);
var tdl = gs.typedDependenciesCCprocessed();
System.Console.WriteLine("\n{0}\n", tdl);
var tp = new TreePrint("penn,typedDependenciesCollapsed");
tp.printTree(parse);
}
public void SentenceParser(string sent2)
{
var modelsDirectory = jarRoot + @"edu\stanford\nlp\models";
// Loading english PCFG parser from file
var lp = LexicalizedParser.loadModel(modelsDirectory + @"\lexparser\englishPCFG.ser.gz");
// This option shows loading and using an explicit tokenizer
sent2.ToLower();
var tokenizerFactory = PTBTokenizer.factory(new CoreLabelTokenFactory(), "");
var sent2Reader = new java.io.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);
ArrayList dep = gs.typedDependenciesCollapsed() as ArrayList;
foreach (TypedDependency td in dep)
{
for (int i = 0; i < keyword.Length; i++)
{
if (td.dep().originalText().Equals(keyword[i]))
{
keyFlag = true;
key = keyword[i];
break;
}
}
if (keyFlag)
{
break;
}
}
keyFlag = false;
switch (key)
{
case "circle":
Circle circle = new Circle();
shape = circle.GetProps();
propsUsed = Associator(shape, dep);
break;
case "rectangle":
Rectangle rect = new Rectangle();
shape = rect.GetProps();
propsUsed = Associator(shape, dep);
break;
case "triangle":
Triangle tri = new Triangle();
shape = tri.GetProps();
propsUsed = Associator(shape, dep);
break;
case "square":
Square square = new Square();
shape = square.GetProps();
propsUsed = Associator(shape, dep);
break;
default:
break;
} //End of Switch
dependency = tdl.ToString();
} //End of SentenceParser
static void Main(string[] args)
{
var tf = new edu.stanford.nlp.trees.LabeledScoredTreeFactory(new CustomStringLabelFactory());
var str = "(x2 / score :null_edge(x1 / null_tag) :null_edge(x3 / null_tag) :time(xap0 / before :quant(x5 / temporal - quantity :unit(y / year) :null_edge(x4 / null_tag))))";
var input = new java.io.StringReader(str);
var treeReader = new edu.stanford.nlp.trees.PennTreeReader(input, tf, new CustomTreeNormalizer(), new CustomTokenizerAdapter(input));
var t = treeReader.readTree();
TreePrint p = new TreePrint("penn");
p.printTree(t);
//READ RST INFORMATION
RSTTree tree = new RSTTree("lincon");
tree.Load(Path.Combine(Root, "rst.xml"));
tree.EvaluateODonell();
var sum = tree.Summarize();
//READ AMR INFORMATION FOR EACH EDU AND ASSOCIATTE THE ODONELL SCORE
IGraph g = new Graph();
var parser = new VDS.RDF.Parsing.RdfXmlParser();
// NTriplesParser ntparser = new NTriplesParser();
parser.Load(g, Path.Combine(Root, "output.xml"));
var document = new AMRDocument();
document.Load(g);
foreach (var item in document.EDUSentences)
{
item.ApplyRSTWeight(sum.Where(c => c.edu == item.Id).Select(c => c.Weight).First());
}
//var rstdocument = new RSTDocumentRepository();
//rstdocument.DeleteAllNodes();
//rstdocument.Save(tree);
AMRNEORepository repo = new AMRNEORepository();
repo.DeleteAllNodes();
repo.SaveDocument(document);
//var ids = Helper.ReadIds(g);
//foreach (var item in ids)
//{
// item.sentence = Helper.GetSentence(g, item);
// item.AddNodes(g);
// if (item.id == 22)
// {
// Console.WriteLine(item.urlid);
// Console.WriteLine(item.sentence);
// Console.WriteLine(item.Root.uriid);
// Console.WriteLine(item.Root.Term.uriid);
// Console.WriteLine(item.Root.Term.type);
// }
//}
//SparqlQueryParser qparser = new SparqlQueryParser();
////Then we can parse a SPARQL string into a query
//StringBuilder querystr = new StringBuilder();
//querystr.AppendLine("PREFIX amr-core: <http://amr.isi.edu/rdf/core-amr#>");
//querystr.AppendLine("PREFIX amr-data: <http://amr.isi.edu/amr_data#>");
//querystr.AppendLine("PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>");
//querystr.AppendLine("PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>");
//querystr.AppendLine("PREFIX amr-terms: <http://amr.isi.edu/rdf/amr-terms#>");
////querystr.AppendLine("SELECT ?p WHERE { ?s rdf:type ?p }");
////querystr.Append("SELECT ?s ?sentence ?id ?root ?rtype ?amrtype");
//querystr.Append("SELECT ?root ?rtype ?amrtypelbl ");
//querystr.Append("WHERE {");
//querystr.Append("?s amr-core:has-sentence ?sentence.");
//querystr.Append("?s amr-core:has-id ?id.");
//querystr.Append("?s amr-core:root ?root. ");
//querystr.Append("?root rdf:type ?rtype. ");
//querystr.Append("?rtype rdf:type ?amrtype. ");
//querystr.Append("?amrtype rdfs:label ?amrtypelbl. ");
//querystr.Append("}");
//SparqlQuery q = qparser.ParseFromString(querystr.ToString());
////http://amr.isi.edu/rdf/core-amr#has-id
//var rset = (SparqlResultSet)g.ExecuteQuery(q);
//var SB = new StringBuilder();
//if (rset.Result && rset.Results.Count > 0)
//{
// foreach (var result in rset.Results)
// {
// foreach (var r in result)
// {
// Console.WriteLine(r.Key + " " + r.Value);
// }
// //Do what you want with each result
// }
//}
//File.WriteAllText("dic.txt", SB.ToString());
//http://amr.isi.edu/amr_data/22#root01
//foreach (var item in g.Triples)
//{
// Console.WriteLine(item.Subject);
//}
//foreach (var node in g.Nodes)
//{
// Console.WriteLine(node.ToString());
//}
//g.SaveToFile("output.rdf");
}