public void Chunker()
{
using var modelIn = new java.io.FileInputStream(GetModel("en-chunker.bin"));
var model = new opennlp.tools.chunker.ChunkerModel(modelIn);
var chunker = new opennlp.tools.chunker.ChunkerME(model);
var sent = new[]
{
"Rockwell", "International", "Corp.", "'s", "Tulsa", "unit", "said", "it", "signed",
"a", "tentative", "agreement", "extending", "its", "contract", "with", "Boeing", "Co.",
"to", "provide", "structural", "parts", "for", "Boeing", "'s", "747", "jetliners", "."
};
var pos = new[]
{
"NNP", "NNP", "NNP", "POS", "NNP", "NN", "VBD", "PRP", "VBD", "DT", "JJ", "NN", "VBG", "PRP$",
"NN", "IN", "NNP", "NNP", "TO", "VB", "JJ", "NNS", "IN", "NNP", "POS", "CD", "NNS", "."
};
var tags = chunker.chunk(sent, pos);
System.Console.WriteLine(string.Join(";", tags));
Assert.AreEqual(28, tags.Length);
var probs = chunker.probs();
System.Console.WriteLine(string.Join(";", probs));
Assert.AreEqual(28, probs.Length);
}
public override void run(string format, string[] args)
{
base.run(format, args);
mlParams = CmdLineUtil.loadTrainingParameters(@params.Params, false);
if (mlParams == null)
{
mlParams = ModelUtil.createTrainingParameters(@params.Iterations.Value, @params.Cutoff.Value);
}
File modelOutFile = @params.Model;
CmdLineUtil.checkOutputFile("sentence detector model", modelOutFile);
ChunkerModel model;
try
{
ChunkerFactory chunkerFactory = ChunkerFactory.create(@params.Factory);
model = ChunkerME.train(@params.Lang, sampleStream, mlParams, chunkerFactory);
}
catch (IOException e)
{
throw new TerminateToolException(-1, "IO error while reading training data or indexing data: " + e.Message, e);
}
finally
{
try
{
sampleStream.close();
}
catch (IOException)
{
// sorry that this can fail
}
}
CmdLineUtil.writeModel("chunker", modelOutFile, model);
}
