public void TestTrigramLanguageModelCreationFromText() { var ngramSize = 3; var languageModel = new NGramLanguageModel(ngramSize); var stream = Tests.OpenFile("/opennlp/tools/languagemodel/sentences.txt", Encoding.UTF8); string line; while ((line = stream.ReadLine()) != null) { var list = new List <string>(line.Split(new[] { ' ' }, StringSplitOptions.None)); var generatedStrings = NGramGenerator.Generate(list, ngramSize, " "); foreach (var generatedString in generatedStrings) { var tokens = generatedString.Split(new[] { ' ' }, StringSplitOptions.None); if (tokens.Length > 0) { languageModel.Add(new StringList(tokens), 1, ngramSize); } } } var predited = languageModel.PredictNextTokens(new StringList("neural", "network", "language")); Assert.That(predited, Is.EqualTo(new StringList("models"))); var p1 = languageModel.CalculateProbability(new StringList("neural", "network", "language", "models")); var p2 = languageModel.CalculateProbability(new StringList("neural", "network", "language", "model")); Assert.That(p1, Is.GreaterThan(p2)); }
public void TestSerializedNGramLanguageModel() { var languageModel = new NGramLanguageModel(Tests.OpenFile("/opennlp/tools/ngram/ngram-model.xml"), 3); var probability = languageModel.CalculateProbability(new StringList("The", "brown", "fox", "jumped")); Assert.That(probability, Is.InRange(0d, 1d), "a probability measure should be between 0 and 1 [was {0} ]", probability); var tokens = languageModel.PredictNextTokens(new StringList("fox")); Assert.That(tokens, Is.EqualTo(new StringList("jumped"))); }
public void TestNgramModel() { var model = new NGramLanguageModel(4) { { new StringList("I", "saw", "the", "fox"), 1, 4 }, { new StringList("the", "red", "house"), 1, 4 }, { new StringList("I", "saw", "something", "nice"), 1, 2 } }; var probability = model.CalculateProbability(new StringList("I", "saw", "the", "red", "house")); Assert.That(probability, Is.InRange(0d, 1d), "a probability measure should be between 0 and 1 [was {0} ]", probability); var tokens = model.PredictNextTokens(new StringList("I", "saw")); Assert.That(tokens, Is.EqualTo(new StringList("the", "fox"))); }