protected internal virtual void SetGlobalHolder(MaxentTagger tagger)
{
foreach (Extractor extractor in v)
{
extractor.SetGlobalHolder(tagger);
}
}
/// <exception cref="System.IO.IOException"/>
public TestClassifier(MaxentTagger maxentTagger, string testFile)
{
// TODO: can we break this class up in some way? Perhaps we can
// spread some functionality into TestSentence and some into MaxentTagger
// TODO: at the very least, it doesn't seem to make sense to make it
// an object with state, rather than just some static methods
// TODO: only one boolean here instead of 4? They all use the same
// debug status
this.maxentTagger = maxentTagger;
this.config = maxentTagger.config;
SetDebug(config.GetDebug());
fileRecord = TaggedFileRecord.CreateRecord(config, testFile);
saveRoot = config.GetDebugPrefix();
if (saveRoot == null || saveRoot.Equals(string.Empty))
{
saveRoot = fileRecord.Filename();
}
Test();
if (writeConfusionMatrix)
{
PrintFile pf = new PrintFile(saveRoot + ".confusion");
pf.Write(confusionMatrix.ToString());
pf.Close();
}
}
public IEnumerable<Tuple<string, PartOfSpeech>> ParseText(string text)
{
var jarRoot = (string) (new AppSettingsReader().GetValue("POSTaggerRoot", typeof (string)));
var modelsDirectory = jarRoot + @"\models";
// Some black magic just to load POS Tagger
CultureInfo ci = new CultureInfo("en-US");
Thread.CurrentThread.CurrentCulture = ci;
Thread.CurrentThread.CurrentUICulture = ci;
var tagger = new MaxentTagger(modelsDirectory + @"\wsj-0-18-bidirectional-nodistsim.tagger");
var sentences = MaxentTagger.tokenizeText(new StringReader(text)).toArray();
// ReSharper disable once LoopCanBeConvertedToQuery
foreach (ArrayList sentence in sentences)
{
var taggedSentence = tagger.tagSentence(sentence).toArray();
foreach (TaggedWord word in taggedSentence)
{
yield return
new Tuple<string, PartOfSpeech>(word.value(),
_nouns.Contains(word.tag()) ? PartOfSpeech.N : PartOfSpeech.X);
}
}
}
public virtual void TestPairsHolder()
{
PairsHolder pairsHolder = new PairsHolder();
for (int i = 0; i < 10; i++)
{
pairsHolder.Add(new WordTag("girl", "NN"));
}
MaxentTagger maxentTagger = new MaxentTagger();
maxentTagger.Init(null);
//maxentTagger.pairs = pairsHolder;
History h = new History(0, 5, 3, pairsHolder, maxentTagger.extractors);
TaggerExperiments te = new TaggerExperiments(maxentTagger);
int x = te.GetHistoryTable().Add(h);
//int x = maxentTagger.tHistories.add(h);
int y = te.GetHistoryTable().GetIndex(h);
//int y = maxentTagger.tHistories.getIndex(h);
NUnit.Framework.Assert.AreEqual("Failing to get same index for history", x, y);
Extractor e = new Extractor(0, false);
string k = e.Extract(h);
NUnit.Framework.Assert.AreEqual("Extractor didn't find stored word", k, "girl");
}
static void Main()
{
var jarRoot = @"C:\Users\Burds\Downloads\Stanford.NLP.NET-master (1)\Stanford.NLP.NET-master\samples\Stanford.NLP.POSTagger.CSharp\bin\Debug\stanford-postagger-2018-02-27";
var modelsDirectory = jarRoot + @"\models";
// Loading POS Tagger
var tagger = new MaxentTagger(modelsDirectory + @"\english-left3words-distsim.tagger");
// Text for tagging
var text = "This is a test sentence.";
string[] arr = new string[10];
var sentences = MaxentTagger.tokenizeText(new StringReader(text)).toArray();
string[] getType = new string[10];
foreach (ArrayList sentence in sentences)
{
var taggedSentence = tagger.tagSentence(sentence);
Console.WriteLine(SentenceUtils.listToString(taggedSentence, false));
var data = new List <DataClass>();
for (int i = 0; i < taggedSentence.size() - 1; i++)
{
string myString = taggedSentence.get(i).ToString();
data.Add(new DataClass
{
SWord = sentence.get(i).ToString(),
WType = myString.Substring(myString.IndexOf("/") + 1)
});
//getType[i] = myString.Substring(myString.IndexOf("/") + 1);
}
}
}
public POSTaggerAnnotator(MaxentTagger model, int maxSentenceLength, int numThreads)
{
this.pos = model;
this.maxSentenceLength = maxSentenceLength;
this.nThreads = numThreads;
this.reuseTags = false;
}
public string TagSentence(string sentence)
{
var tokenizedSentence = (ArrayList)MaxentTagger.tokenizeText(new StringReader(sentence)).get(0);
var taggedSentence = _tagger.tagSentence(tokenizedSentence).toArray();
return(string.Join(" ", taggedSentence));
}
static void Main(string[] args)
{
var jarRoot = @"F:\Downloads\stanford-postagger-full-2015-01-30";
var modelsDirectory = jarRoot + @"\models";
// Loading POS Tagger
var tagger = new MaxentTagger(modelsDirectory + @"\wsj-0-18-bidirectional-nodistsim.tagger");
// Text for tagging
var text = "I'm not happy.";
var sentences = MaxentTagger.tokenizeText(new StringReader(text)).toArray();
foreach (ArrayList sentence in sentences)
{
var taggedSentence = tagger.tagSentence(sentence);
Iterator it = taggedSentence.iterator();
while (it.hasNext())
{
var item = it.next().ToString();
var split = item.Split('/');
var word = split[0];
var pos = split[1];
Console.WriteLine("Word:" + word + " POS:" + pos);
}
Console.ReadLine();
}
}
static void Main(string[] args)
{
// Loading POS Tagger
var tagger = new MaxentTagger(@"Resources/english-bidirectional-distsim.tagger");
// Text for tagging
//var text = @"یک روز آمدم ";
var text = "hello how are you?";
IList <Tuple <string, string> > tagged = new List <Tuple <string, string> >();
var sentences = MaxentTagger.tokenizeText(new StringReader(text)).toArray();
foreach (ArrayList sentence in sentences)
{
var taggedSentence = tagger.tagSentence(sentence);
System.Console.WriteLine(SentenceUtils.listToString(taggedSentence, false));
for (int i = 0; i < taggedSentence.size(); i++)
{
var t = taggedSentence.toArray()[i].ToString().Split('/');
tagged.Add(Tuple.Create(t[0], t[1]));
}
}
}
/// <exception cref="System.Exception"/>
public static void Main(string[] args)
{
if (args.Length != 2)
{
log.Info("usage: java TaggerDemo2 modelFile fileToTag");
return;
}
MaxentTagger tagger = new MaxentTagger(args[0]);
ITokenizerFactory <CoreLabel> ptbTokenizerFactory = PTBTokenizer.Factory(new CoreLabelTokenFactory(), "untokenizable=noneKeep");
BufferedReader r = new BufferedReader(new InputStreamReader(new FileInputStream(args[1]), "utf-8"));
PrintWriter pw = new PrintWriter(new OutputStreamWriter(System.Console.Out, "utf-8"));
DocumentPreprocessor documentPreprocessor = new DocumentPreprocessor(r);
documentPreprocessor.SetTokenizerFactory(ptbTokenizerFactory);
foreach (IList <IHasWord> sentence in documentPreprocessor)
{
IList <TaggedWord> tSentence = tagger.TagSentence(sentence);
pw.Println(SentenceUtils.ListToString(tSentence, false));
}
// print the adjectives in one more sentence. This shows how to get at words and tags in a tagged sentence.
IList <IHasWord> sent = SentenceUtils.ToWordList("The", "slimy", "slug", "crawled", "over", "the", "long", ",", "green", "grass", ".");
IList <TaggedWord> taggedSent = tagger.TagSentence(sent);
foreach (TaggedWord tw in taggedSent)
{
if (tw.Tag().StartsWith("JJ"))
{
pw.Println(tw.Word());
}
}
pw.Close();
}
private List <Token> TokenizeandTag(string rawText)
{
var sentences = MaxentTagger.tokenizeText(new java.io.StringReader(rawText));
var tokenList = new List <Token>();
foreach (List o in sentences.toArray())
{
if (PosTagger == null)
{
tokenList.AddRange(o
.toArray()
.Cast <HasWord>()
.Select(w => new Token
{
Text = w.word(),
PartOfSpeech = "SYM"
}));
}
else
{
tokenList.AddRange(PosTagger
.tagSentence(o)
.toArray()
.Cast <TaggedWord>()
.Select(w => new Token
{
Text = w.word(),
PartOfSpeech = w.tag()
}));
}
}
return(tokenList);
}
public void LoadPOSTagger()
{
var jarRoot = @"C:\Users\nahide\Documents\DataScience\IR\TheApplication\TheApplication\TheApplication\stanford-english-corenlp-2016-01-10-models\edu\stanford\nlp";
var modelsDirectory = jarRoot + @"\models\pos-tagger";
// Loading POS Tagger
tagger = new MaxentTagger(modelsDirectory + @"\wsj-0-18-bidirectional-nodistsim.tagger");
}
private static void initialLanguagePattern()
{
//URL Düzelt
var jarRoot = @"J:\ToltecSoft.WebCrawler";
var modelsDirectory = jarRoot + @"\models";
tagger = new MaxentTagger(modelsDirectory + @"\english-left3words-distsim.tagger");
}
public StanfordPosTagger()
{
var jarRoot = @"d:\code\NLP\Tests\Test0\lib\stanford-postagger-full-2015-01-30";
var modelsDirectory = jarRoot + @"\models";
// Loading POS Tagger
tagger = new MaxentTagger(modelsDirectory + @"\french.tagger");
}
internal TaggerExperiments(MaxentTagger maxentTagger)
{
// This constructor is only used by unit tests.
this.maxentTagger = maxentTagger;
this.tFeature = new TemplateHash(maxentTagger);
numFeatsGeneral = maxentTagger.extractors.Size();
numFeatsAll = numFeatsGeneral + maxentTagger.extractorsRare.Size();
feats = new TaggerFeatures(this);
}
public PosTagger()
{
if (!File.Exists(modelPath))
{
File.WriteAllBytes(modelPath, Properties.Resources.Model);
}
tagger = new MaxentTagger(modelPath, new java.util.Properties(), false);
}
public PartOfSpeech(POSMode posMode)
{
_modelPath = _modelPath + GetPOSModel(posMode);
if (!System.IO.File.Exists(_modelPath))
{
throw new Exception($"Check path to the model file '{_modelPath}'");
}
_tagger = new MaxentTagger(_modelPath);
}
private static void TagReader(Reader reader)
{
var tagger = new MaxentTagger(Model);
foreach (List sentence in MaxentTagger.tokenizeText(reader).toArray())
{
var tSentence = tagger.tagSentence(sentence);
System.Console.WriteLine(Sentence.listToString(tSentence, false));
}
}
private static void TagReader(Reader reader)
{
var tagger = new MaxentTagger(Model);
foreach (List sentence in MaxentTagger.tokenizeText(reader).toArray())
{
var tSentence = tagger.tagSentence(sentence);
System.Console.WriteLine(Sentence.listToString(tSentence, false));
}
}
public Interpreter(IRegistrar registrar, bool usePosTagger = true)
{
var baseDir = AppDomain.CurrentDomain.BaseDirectory;
_entries = registrar.Entries;
if (usePosTagger)
{
PosTagger = new MaxentTagger(
Path.Combine(baseDir, "data", "english-bidirectional-distsim.tagger"));
}
}
internal static void InitMaxentTagger()
{
var model = PathToModel();
if (string.IsNullOrWhiteSpace(model))
{
throw new ItsDeadJim("Could not resolve the .tagger models path.");
}
_mt = new MaxentTagger(model);
}
// Text for tagging
public void FindPOS(string querytext)
{
MaxentTagger tagger = new MaxentTagger();
StringReader stringReader = new StringReader(querytext);
Array inputSentances = MaxentTagger.tokenizeText(stringReader).toArray();
foreach (java.util.ArrayList sentance in inputSentances)
{
var taggedSentence = tagger.tagSentence(sentance);
}
}
public StanfordPosTagger(string strDataPath_)
{
lock (taggerlock)
{
if (datapath != strDataPath_)
{
datapath = strDataPath_;
tagger = null;
}
}
}
/// <summary>
/// Initializes a new instance of the <see cref="Preprocessor" /> class.
/// </summary>
public Preprocessor()
{
listLatestTokenizedArticle = new List <Token>();
listWhoCandidates = new List <Candidate>();
listWhenCandidates = new List <Candidate>();
listWhereCandidates = new List <Candidate>();
listWhatCandidates = new List <List <Token> >();
listWhyCandidates = new List <List <Token> >();
nerClassifier = CRFClassifier.getClassifierNoExceptions(nerModelPath);
posTagger = new MaxentTagger(posModelPath);
}
public Interpreter(IRegistrar registrar, bool usePosTagger = true)
{
var baseDir = AppDomain.CurrentDomain.BaseDirectory;
_entries = registrar.Entries;
if (usePosTagger)
{
PosTagger = new MaxentTagger(
Path.Combine(baseDir, "data", "english-bidirectional-distsim.tagger"));
}
}
public static IList <Tuple <string, string> > getTags(string santance, string lang)
{
MaxentTagger tagger;
string lng = lang;
try
{
//if ( Regex.IsMatch(santance, @"^[\u0000-\u007F]+$"))
//{
// lng = "english";
//}
//tagger = new MaxentTagger(@"Resources/"+ lng +".tagger");
string ResurchPath = System.IO.Path.GetDirectoryName(Assembly.GetExecutingAssembly().Location) + @"\Resources\" + lng + ".tagger";
if (!System.IO.File.Exists(ResurchPath))
{
throw new Exception("resource not found " + ResurchPath);
}
tagger = new MaxentTagger(ResurchPath);
IList <Tuple <string, string> > tagged = new List <Tuple <string, string> >();
// Text for tagging
//var text = @"یک روز آمدم ";
var text = santance;// "hello how are you?";
var sentences = MaxentTagger.tokenizeText(new StringReader(text)).toArray();
foreach (ArrayList sentence in sentences)
{
var taggedSentence = tagger.tagSentence(sentence);
//System.Console.WriteLine(SentenceUtils.listToString(taggedSentence, false));
for (int i = 0; i < taggedSentence.size(); i++)
{
var t = taggedSentence.toArray()[i].ToString().Split('/');
tagged.Add(Tuple.Create(t[0], t[1]));
}
}
return(tagged);
}
catch (Exception ex)
{
System.Console.WriteLine(ex.Message);
return(null);
}
finally
{
tagger = null;
}
}
public Preprocessor()
{
listLatestTokenizedArticle = new List<Token>();
listWhoCandidates = new List<Candidate>();
listWhenCandidates = new List<Candidate>();
listWhereCandidates = new List<Candidate>();
listWhatCandidates = new List<List<Token>>();
listWhyCandidates = new List<List<Token>>();
nerClassifier = CRFClassifier.getClassifierNoExceptions(nerModelPath);
posTagger = new MaxentTagger(posModelPath);
}
public void MaxentTaggerTest()
{
// Plain model in the file
var model = Files.Parser.Models("pos-tagger/english-left3words-distsim.tagger");
using var fs = new FileStream(model, FileMode.Open);
using var isw = new ikvm.io.InputStreamWrapper(fs);
var tagger = new MaxentTagger(isw);
Assert.NotNull(tagger);
}
public string TagSentences(string text)
{
var tokenizedSentences = (ArrayList)MaxentTagger.tokenizeText(new StringReader(text));
var taggedSentences = _tagger.process(tokenizedSentences) as ArrayList;
var result = new StringBuilder();
foreach (ArrayList sentence in taggedSentences)
{
result.Append(string.Join(" ", sentence.toArray()));
}
return(result.ToString());
}
private void TagReader(Reader reader)
{
var sentences = MaxentTagger.tokenizeText(reader).toArray();
Assert.NotNull(sentences);
foreach (ArrayList sentence in sentences)
{
var tSentence = _tagger.tagSentence(sentence);
TestContext.Out.WriteLine(SentenceUtils.listToString(tSentence, false));
}
}
private string POSTagger(string text)
{
string posSentence = string.Empty;
var sentences = MaxentTagger.tokenizeText(new java.io.StringReader(text)).toArray();
foreach (ArrayList sentence in sentences)
{
var taggedSentence = tagger.tagSentence(sentence);
posSentence += Sentence.listToString(taggedSentence, false);
}
return(posSentence);
}
//private static SentenceParse instance;
public SentenceParse()
{
//dictionaryService=new ViconDictionaryService();
string currentFolder = Path.GetDirectoryName(Assembly.GetExecutingAssembly().Location);
var model = currentFolder + @"\models\english-bidirectional-distsim.tagger";
// Loading POS Tagger
if (tagger == null)
{
tagger = new MaxentTagger(model);
}
}
public static void Execute(string fileName)
{
var tagger = new MaxentTagger(TaggerDemo.Model);
var ptbTokenizerFactory = PTBTokenizer.factory(new CoreLabelTokenFactory(), "untokenizable=noneKeep");
var r = new BufferedReader(new InputStreamReader(new FileInputStream(fileName), "utf-8"));
var documentPreprocessor = new DocumentPreprocessor(r);
documentPreprocessor.setTokenizerFactory(ptbTokenizerFactory);
foreach (List sentence in documentPreprocessor)
{
var tSentence = tagger.tagSentence(sentence);
System.Console.WriteLine(Sentence.listToString(tSentence, false));
}
}
public static Result <string> GetTag(this MaxentTagger tagger, string word)
{
try
{
return(tagger.tagString(word)
.Split('_')
.Last()
.TrimEnd());
}
catch (InvalidOperationException ex)
{
return(Fail <string>(ex.Message));
}
}
public static void Execute(string fileName)
{
var tagger = new MaxentTagger(TaggerDemo.Model);
var ptbTokenizerFactory = PTBTokenizer.factory(new CoreLabelTokenFactory(), "untokenizable=noneKeep");
var r = new BufferedReader(new InputStreamReader(new FileInputStream(fileName), "utf-8"));
var documentPreprocessor = new DocumentPreprocessor(r);
documentPreprocessor.setTokenizerFactory(ptbTokenizerFactory);
foreach (List sentence in documentPreprocessor)
{
var tSentence = tagger.tagSentence(sentence);
System.Console.WriteLine(Sentence.listToString(tSentence, false));
}
}
private void TagReader(Reader reader)
{
var tagger = new MaxentTagger(Model);
//List obj = (List)MaxentTagger.tokenizeText(reader);
foreach (ArrayList sentence in MaxentTagger.tokenizeText(reader).toArray())
{
var tSentence = tagger.tagSentence(sentence);
System.Console.WriteLine(Sentence.listToString(tSentence, false));
posstring = (Sentence.listToString(tSentence, false));
newString = newString + posstring;
System.Console.WriteLine();
}
}
public void ThreeInterestingDates()
{
var pipeline = new AnnotationPipeline();
pipeline.addAnnotator(new TokenizerAnnotator(false));
pipeline.addAnnotator(new WordsToSentencesAnnotator(false));
var filePath = Files.CoreNlp.Models("pos-tagger/english-left3words-distsim.tagger");
var tagger = new MaxentTagger(filePath);
pipeline.addAnnotator(new POSTaggerAnnotator(tagger));
var props = Java.Props(new Dictionary <string, string>
{
{ "sutime.binders", "0" },
{
"sutime.rules", string.Join(",",
Files.CoreNlp.Models("sutime/defs.sutime.txt"),
Files.CoreNlp.Models("sutime/english.sutime.txt"),
Files.CoreNlp.Models("sutime/english.holidays.sutime.txt"))
}
});
pipeline.addAnnotator(new TimeAnnotator("sutime", props));
var text = "Three interesting dates are 18 Feb 1997, the 20th of july and 4 days from today.";
var annotation = new Annotation(text);
annotation.set(Java.GetAnnotationClass <CoreAnnotations.DocDateAnnotation>(), "2013-07-14");
pipeline.annotate(annotation);
TestContext.Out.WriteLine(annotation.get(Java.GetAnnotationClass <CoreAnnotations.TextAnnotation>()));
var timexAnnsAll = (java.util.ArrayList)annotation.get(Java.GetAnnotationClass <TimeAnnotations.TimexAnnotations>());
Assert.Greater(timexAnnsAll.size(), 0);
foreach (CoreMap cm in timexAnnsAll)
{
var tokens = (java.util.List)cm.get(Java.GetAnnotationClass <CoreAnnotations.TokensAnnotation>());
Assert.Greater(tokens.size(), 0);
var first = tokens.get(0);
var last = tokens.get(tokens.size() - 1);
var time = (TimeExpression)cm.get(Java.GetAnnotationClass <TimeExpression.Annotation>());
Assert.IsNotNull(time, "Time expression is null");
TestContext.Out.WriteLine($"{cm} [from char offset '{first}' to '{last}'] --> {time.getTemporal()}");
}
}
public POSTagger()
{
#if DEBUG
tagger = new MaxentTagger(modelPath);
#else
try
{
tagger = new MaxentTagger(modelPath);
}
catch (Exception e)
{
tagger = null;
}
#endif
}
static void Main(string[] args)
{
var tagger = new MaxentTagger(wsjtagger);
// Text for tagging
// Intent of the command
// Variations of the command - all mapped to the same intent.
// find antony in test.txt -
//
var sentences = MaxentTagger.tokenizeText(new StringReader(text)).toArray();
foreach (ArrayList sentence in sentences)
{
var taggedSentence = tagger.tagSentence(sentence);
Console.WriteLine(Sentence.listToString(taggedSentence, false));
}
}
private static void Main()
{
// Path to the folder with models extracted from `stanford-corenlp-3.6.0-models.jar`
var jarRoot = @"..\..\..\..\paket-files\nlp.stanford.edu\stanford-corenlp-full-2015-12-09\models";
var modelsDirectory = jarRoot + @"\edu\stanford\nlp\models";
// Annotation pipeline configuration
var pipeline = new AnnotationPipeline();
pipeline.addAnnotator(new TokenizerAnnotator(false));
pipeline.addAnnotator(new WordsToSentencesAnnotator(false));
// Loading POS Tagger and including them into pipeline
var tagger = new MaxentTagger(modelsDirectory +
@"\pos-tagger\english-bidirectional\english-bidirectional-distsim.tagger");
pipeline.addAnnotator(new POSTaggerAnnotator(tagger));
// SUTime configuration
var sutimeRules = modelsDirectory + @"\sutime\defs.sutime.txt,"
+ modelsDirectory + @"\sutime\english.holidays.sutime.txt,"
+ modelsDirectory + @"\sutime\english.sutime.txt";
var props = new Properties();
props.setProperty("sutime.rules", sutimeRules);
props.setProperty("sutime.binders", "0");
pipeline.addAnnotator(new TimeAnnotator("sutime", props));
// Sample text for time expression extraction
var text = "Three interesting dates are 18 Feb 1997, the 20th of july and 4 days from today.";
var annotation = new Annotation(text);
annotation.set(new CoreAnnotations.DocDateAnnotation().getClass(), "2013-07-14");
pipeline.annotate(annotation);
Console.WriteLine("{0}\n", annotation.get(new CoreAnnotations.TextAnnotation().getClass()));
var timexAnnsAll = annotation.get(new TimeAnnotations.TimexAnnotations().getClass()) as ArrayList;
foreach (CoreMap cm in timexAnnsAll)
{
var tokens = cm.get(new CoreAnnotations.TokensAnnotation().getClass()) as List;
var first = tokens.get(0);
var last = tokens.get(tokens.size() - 1);
var time = cm.get(new TimeExpression.Annotation().getClass()) as TimeExpression;
Console.WriteLine("{0} [from char offset {1} to {2}] --> {3}", cm, first, last, time.getTemporal());
}
}
private Annotation PrepareAnnotation(string text, DateTime currentDate)
{
var pipeline = new AnnotationPipeline();
pipeline.addAnnotator(new TokenizerAnnotator(false));
pipeline.addAnnotator(new WordsToSentencesAnnotator(false));
var tagger = new MaxentTagger(modelsDir + @"pos-tagger\english-bidirectional\english-bidirectional-distsim.tagger");
pipeline.addAnnotator(new POSTaggerAnnotator(tagger));
var sutimeRules = modelsDir + @"\sutime\defs.sutime.txt,"
+ modelsDir + @"\sutime\english.holidays.sutime.txt,"
+ modelsDir + @"\sutime\english.sutime.txt";
var props = new Properties();
props.setProperty("sutime.rules", sutimeRules);
props.setProperty("sutime.binders", "0");
pipeline.addAnnotator(new TimeAnnotator("sutime", props));
var annotation = new Annotation(text);
annotation.set(new CoreAnnotations.DocDateAnnotation().getClass(), currentDate.ToString("yyyy-MM-dd"));
pipeline.annotate(annotation);
return annotation;
}
static void Main()
{
var jarRoot = @"..\..\..\..\paket-files\nlp.stanford.edu\stanford-postagger-full-2015-12-09";
var modelsDirectory = jarRoot + @"\models";
// Loading POS Tagger
var tagger = new MaxentTagger(modelsDirectory + @"\wsj-0-18-bidirectional-nodistsim.tagger");
// Text for tagging
var text = "A Part-Of-Speech Tagger (POS Tagger) is a piece of software that reads text in some language "
+"and assigns parts of speech to each word (and other token), such as noun, verb, adjective, etc., although "
+ "generally computational applications use more fine-grained POS tags like 'noun-plural'.";
var sentences = MaxentTagger.tokenizeText(new StringReader(text)).toArray();
foreach (ArrayList sentence in sentences)
{
var taggedSentence = tagger.tagSentence(sentence);
Console.WriteLine(Sentence.listToString(taggedSentence, false));
}
}
public void SUTimeDefautTest()
{
var pipeline = new AnnotationPipeline();
pipeline.addAnnotator(new PTBTokenizerAnnotator(false));
pipeline.addAnnotator(new WordsToSentencesAnnotator(false));
var tagger =
new MaxentTagger(
Config.GetModel(@"pos-tagger\english-bidirectional\english-bidirectional-distsim.tagger"));
pipeline.addAnnotator(new POSTaggerAnnotator(tagger));
var sutimeRules = new[] {
Config.GetModel(@"sutime\defs.sutime.txt"),
Config.GetModel(@"sutime\english.holidays.sutime.txt"),
Config.GetModel(@"sutime\english.sutime.txt")
};
var props = new Properties();
props.setProperty("sutime.rules", String.Join(",", sutimeRules));
props.setProperty("sutime.binders", "0");
pipeline.addAnnotator(new TimeAnnotator("sutime", props));
const string text = "Three interesting dates are 18 Feb 1997, the 20th of july and 4 days from today.";
var annotation = new Annotation(text);
annotation.set(new CoreAnnotations.DocDateAnnotation().getClass(), "2013-07-14");
pipeline.annotate(annotation);
Console.WriteLine(annotation.get(new CoreAnnotations.TextAnnotation().getClass())+"\n");
var timexAnnsAll = (ArrayList)annotation.get(new TimeAnnotations.TimexAnnotations().getClass());
foreach (CoreMap cm in timexAnnsAll)
{
var tokens = (java.util.List)cm.get(new CoreAnnotations.TokensAnnotation().getClass());
var first = tokens.get(0);
var last = tokens.get(tokens.size() - 1);
var time = (TimeExpression)cm.get(new TimeExpression.Annotation().getClass());
Console.WriteLine("{0} [from char offset '{1}' to '{2}'] --> {3}",
cm, first, last, (time.getTemporal()));
}
}
public bool InitTagger()
{
lock (taggerlock)
{
if (tagger == null)
{
tagger = new MaxentTagger(datapath);
}
}
return true;
}
//private static SentenceParse instance;
public SentenceParse()
{
//dictionaryService=new ViconDictionaryService();
//string currentFolder = Path.GetDirectoryName(Assembly.GetExecutingAssembly().Location);
string currentFolder = System.AppDomain.CurrentDomain.BaseDirectory;
var model = currentFolder + @"\models\english-bidirectional-distsim.tagger";
// Loading POS Tagger
if(tagger==null)
tagger = new MaxentTagger(model);
}
public void extractTime(string text)
{
sentenceInput = text;
string presentDate = "2015-10-10";
string curr = Environment.CurrentDirectory;
var jarRoot = curr + @"\stanford-corenlp-3.5.2-models";
var modelsDirectory = jarRoot + @"\edu\stanford\nlp\models";
// Annotation pipeline configuration
var pipeline = new AnnotationPipeline();
pipeline.addAnnotator(new TokenizerAnnotator(false));
pipeline.addAnnotator(new WordsToSentencesAnnotator(false));
// SUTime configuration
var sutimeRules = modelsDirectory + @"\sutime\defs.sutime.txt,"
+ modelsDirectory + @"\sutime\english.holidays.sutime.txt,"
+ modelsDirectory + @"\sutime\english.sutime.txt";
var props = new Properties();
props.setProperty("sutime.rules", sutimeRules);
props.setProperty("sutime.binders", "0");
props.setProperty("sutime.markTimeRanges", "true");
props.setProperty("sutime.includeRange", "true");
pipeline.addAnnotator(new TimeAnnotator("sutime", props));
// Sample text for time expression extraction
var annotation = new Annotation(text);
annotation.set(new CoreAnnotations.DocDateAnnotation().getClass(), presentDate);
pipeline.annotate(annotation);
// Console.WriteLine("{0}\n", annotation.get(new CoreAnnotations.TextAnnotation().getClass()));
var timexAnnsAll = annotation.get(new TimeAnnotations.TimexAnnotations().getClass()) as ArrayList;
foreach (CoreMap cm in timexAnnsAll)
{
var time = cm.get(new TimeExpression.Annotation().getClass()) as TimeExpression;
string typeTimex = time.getTemporal().getTimexType().toString();
if (typeTimex.ToLower() == "duration")
{
typeTime = "tPeriod";
valueTime = time.getTemporal().toISOString();
Console.WriteLine(valueTime);
}
if (typeTimex.ToLower() == "time" || typeTimex.ToLower() == "date")
{
string textOftime = time.getText().ToString();
char[] delimiterChars = { ' ' };
string[] words = textOftime.Split(delimiterChars);
string mainword = words[0];
var tagger = new MaxentTagger(modelsDirectory + @"\pos-tagger\english-bidirectional\english-bidirectional-distsim.tagger");
var sentences = MaxentTagger.tokenizeText(new StringReader(text));
var first = sentences.get(0) as ArrayList;
int size = first.size();
int i = 0;
int index = -3;
while (i < size)
{
if (first.get(i).ToString() == mainword)
index = i;
i++;
}
var taggedSentence = tagger.tagSentence(first);
string checker = taggedSentence.get(index - 1).ToString();
if (checker.ToLower() == "after/in" || checker.ToLower() == "since/in")
{
typeTime = "tTrigger";
valueTime = "Start : " + time.getTemporal().toISOString();
Console.WriteLine(valueTime);
}
else if (checker.ToLower() == "before/in")
{
if (typeTimex == "TIME")
{
typeTime = "tTrigger";
valueTime = "End : " + time.getTemporal().toISOString();
Console.WriteLine(valueTime);
}
else
{
DateTime result = new DateTime();
DateTime current = DateTime.ParseExact(presentDate, "yyyy-MM-dd", System.Globalization.CultureInfo.InvariantCulture);
string dt = time.getTemporal().toString();
char[] delimiter = { '-', '-', '-' };
string[] partsOfDate = time.getTemporal().toISOString().Split(delimiter);
int count = partsOfDate.Length;
if (count == 1)
{
result = Convert.ToDateTime("01-01-" + partsOfDate[0]);
}
if (count == 2)
{
result = Convert.ToDateTime("01-" + partsOfDate[1] + "-" + partsOfDate[0]);
}
// result = DateTime.ParseExact(dt, "yyyy-MM-dd", System.Globalization.CultureInfo.InvariantCulture);
int comp = DateTime.Compare(current, result);
if (comp < 0)
{
typeTime = "tTrigger";
valueTime = "Start now (" + presentDate + ") End :" + time.getTemporal().toString();
Console.WriteLine(valueTime);
}
else
{
typeTime = "tTrigger";
valueTime = "End : " + time.getTemporal().toString();
Console.WriteLine(valueTime);
}
}
}
else
{
typeTime = "tStamp";
valueTime = time.getTemporal().toISOString();
Console.WriteLine(valueTime);
}
}
}
}
private string POS(string OriginalSentence)
{
//POStag tool opposite path
string ToolPath = @"..\..\stanford-postagger-full-2015-04-20\models\wsj-0-18-bidirectional-nodistsim.tagger";
MaxentTagger POStagger = new MaxentTagger(ToolPath);
string POSsentence = "";
object[] sentences = MaxentTagger.tokenizeText(new java.io.StringReader(OriginalSentence)).toArray();
foreach (ArrayList sentence in sentences)
{
var taggedSentence = POStagger.tagSentence(sentence);
POSsentence += Sentence.listToString(taggedSentence, false);
POSsentence += "\n";
}
return POSsentence;
}
public POSTagger(string pathToModel)
{
this._tagger = new MaxentTagger(pathToModel);
}
static PartOfSpeech()
{
var jarRoot = System.IO.Path.Combine(System.IO.Directory.GetParent(System.IO.Directory.GetCurrentDirectory()).Parent.Parent.FullName, @"utility\stanford-postagger-full-2015-01-30");
var modelsDirectory = jarRoot + @"\models";
tagger = new MaxentTagger(modelsDirectory + @"\wsj-0-18-bidirectional-nodistsim.tagger");
}