public void Tokenization()
{
using var modelIn = new java.io.FileInputStream(GetModel("en-token.bin"));
var model = new opennlp.tools.tokenize.TokenizerModel(modelIn);
var tokenizer = new opennlp.tools.tokenize.TokenizerME(model);
var tokens = tokenizer.tokenize("An input sample sentence.");
System.Console.WriteLine(string.Join(";", tokens));
Assert.AreEqual(5, tokens.Length);
}
public void TestCrossCompatibility()
{
using (var data = Tests.OpenFile("/opennlp/tools/tokenize/token.train")) {
var samples = new TokenSampleStream(new PlainTextByLineStream(data));
var mlParams = new TrainingParameters();
mlParams.Set(Parameters.Iterations, "100");
mlParams.Set(Parameters.Cutoff, "0");
var model = TokenizerME.Train(samples, new TokenizerFactory("en", null, true), mlParams);
var sMe = new TokenizerME(model);
TokenizerMETest.TestTokenizer(sMe);
var sProbs = sMe.TokenProbabilities;
// --- java \/
var sFile = Path.GetTempFileName();
model.Serialize(new FileStream(sFile, FileMode.Create));
var jModel = new opennlp.tools.tokenize.TokenizerModel(
OpenNLP.CreateInputStream(sFile)
);
var jMe = new opennlp.tools.tokenize.TokenizerME(jModel);
TestJavaTokenizer(jMe);
var jProbs = jMe.getTokenProbabilities();
Assert.AreEqual(jProbs.Length, sProbs.Length);
for (int i = 0; i < jProbs.Length; i++)
{
// one difference :(
// -0.00000000000000011102230246251565
//
// but still "insignificant" :)
Assert.AreEqual(jProbs[i], sProbs[i], 0.0000000001d);
}
}
}
private opennlp.tools.tokenize.TokenizerME prepareTokenizer()
{
java.io.FileInputStream tokenInputStream = new java.io.FileInputStream(tokenModelPath); //load the token model into a stream
opennlp.tools.tokenize.TokenizerModel tokenModel = new opennlp.tools.tokenize.TokenizerModel(tokenInputStream); //load the token model
return new opennlp.tools.tokenize.TokenizerME(tokenModel); //create the tokenizer
}
public void TestCrossCompatibility() {
using (var data = Tests.OpenFile("/opennlp/tools/tokenize/token.train")) {
var samples = new TokenSampleStream(new PlainTextByLineStream(data));
var mlParams = new TrainingParameters();
mlParams.Set(Parameters.Iterations, "100");
mlParams.Set(Parameters.Cutoff, "0");
var model = TokenizerME.Train(samples, new TokenizerFactory("en", null, true), mlParams);
var sMe = new TokenizerME(model);
TokenizerMETest.TestTokenizer(sMe);
var sProbs = sMe.TokenProbabilities;
// --- java \/
var sFile = Path.GetTempFileName();
model.Serialize(new FileStream(sFile, FileMode.Create));
var jModel = new opennlp.tools.tokenize.TokenizerModel(
OpenNLP.CreateInputStream(sFile)
);
var jMe = new opennlp.tools.tokenize.TokenizerME(jModel);
TestJavaTokenizer(jMe);
var jProbs = jMe.getTokenProbabilities();
Assert.AreEqual(jProbs.Length, sProbs.Length);
for (int i = 0; i < jProbs.Length; i++) {
// one difference :(
// -0.00000000000000011102230246251565
//
// but still "insignificant" :)
Assert.AreEqual(jProbs[i], sProbs[i], 0.0000000001d);
}
}
}
// Constructors and finalizers:
private Repository()
{
_assemblyName = Regex.Match(_assemblyFullName, "^(.*?),.*$").Result("$1");
_rootDrive = ("/usr/project/xtmp/dp195/Poetix18/").Replace(@"\", Dsc);
_nlpFolder = ("rhetorica/nlp/").Replace(@"\", Dsc);
_openNlpModelsFolder = ("OpenNLP/models/").Replace(@"\", Dsc);
_openNlpModelsPath = RootDrive + _nlpFolder + _openNlpModelsFolder;
_wordNetFolder = ("WordNet_3/").Replace(@"\", Dsc);
_wordNetPath = RootDrive + _nlpFolder + _wordNetFolder;
_grammarFolder = ("StanfordParser/grammar/").Replace(@"\", Dsc);
_grammarPath = RootDrive + _nlpFolder + _grammarFolder;
_dataFolder = ("data/").Replace(@"\", Dsc);
_nlpTextsPath = RootDrive + _dataFolder;
string[] localTextDirectoryParts =
{
CurrentAssemblyDirectoryPath,
"..", "..","..", "data"
//"..", "..", "text"
};
_localTextPath = Path.Combine(localTextDirectoryParts) + "/"; // For development use
// WordNet engine:
Console.Write("Loading WordNet engine.... ");
_wordNetEngine = new WordNetEngine(WordNetPath, true);
Console.WriteLine("Done.");
// OpenNLP sentence detector:
Console.Write("Loading OpenNLP sentence detector.... ");
java.io.FileInputStream modelInputStream = new java.io.FileInputStream(OpenNlpModelsPath + "en-sent.bin");
_sentenceModel = new SentenceModel(modelInputStream);
modelInputStream.close();
_sentenceDetector = new SentenceDetectorME(_sentenceModel);
Console.WriteLine("Done.");
// OpenNLP tokenizer:
Console.Write("Loading OpenNLP tokenizer.... ");
modelInputStream = new java.io.FileInputStream(OpenNlpModelsPath + "en-token.bin");
_tokenizerModel = new opennlp.tools.tokenize.TokenizerModel(modelInputStream);
modelInputStream.close();
_tokenizer = new opennlp.tools.tokenize.TokenizerME(_tokenizerModel);
Console.WriteLine("Done.");
// OpenNLP name finder:
Console.Write("Loading OpenNLP name finder.... ");
modelInputStream = new java.io.FileInputStream(OpenNlpModelsPath + "en-ner-person.bin");
_tokenNameFinderModel = new TokenNameFinderModel(modelInputStream);
modelInputStream.close();
_nameFinder = new NameFinderME(_tokenNameFinderModel);
Console.WriteLine("Done.");
// OpenNLP POS tagger:
Console.Write("Loading OpenNLP POS tagger.... ");
modelInputStream = new java.io.FileInputStream(OpenNlpModelsPath + "en-pos-maxent.bin");
_posModel = new POSModel(modelInputStream);
modelInputStream.close();
_tagger = new POSTaggerME(_posModel);
Console.WriteLine("Done.");
// OpenNLP chunker:
Console.Write("Loading OpenNLP chunker.... ");
modelInputStream = new java.io.FileInputStream(OpenNlpModelsPath + "en-chunker.bin");
_chunkerModel = new ChunkerModel(modelInputStream);
modelInputStream.close();
_chunker = new ChunkerME(_chunkerModel);
Console.WriteLine("Done.");
// OpenNLP parser:
if (_loadParser)
{
Console.Write("Loading OpenNLP parser.... ");
modelInputStream = new java.io.FileInputStream(OpenNlpModelsPath + "en-parser-chunking.bin");
_parserModel = new ParserModel(modelInputStream);
modelInputStream.close();
_parser = ParserFactory.create(_parserModel);
Console.WriteLine("Done.");
}
// Stanford parser:
//_stanfordParser = new LexicalizedParser(GrammarPath + "englishPCFG.ser.gz"); // Obsolete method
_stanfordParser = LexicalizedParser.loadModel(GrammarPath + "englishPCFG.ser.gz");
// Porter stemmer:
_porterStemmer = new PorterStemmer();
}