Examples of cc.mallet.grmm.learning.GenericAcrfData2TokenSequence

Generic pipe that takes a linegroup of the form:

 LABEL1 LABEL2 ... LABELk word feature1 feature2 ... featuren

and converts it into an input FeatureVectorSequence and target LabelsSequence.

If the number of labels at each sequence position could vary, then use this format instead:

 LABEL1 LABEL2 ... LABELk ---- word feature1 feature2 ... featuren

The four dashes ---- must be there to separate the features from the labels. Whitespace is ignored. The difference between this pipe and {@link edu.umass.cs.iesl.casutton.experiments.dcrf.GenericDcrfPipe} is that this pipeallows for a different number of labels at each sequence position.

Explicitly specifying which word is the token allows the use of the HTML output from the extract package. Created: Aug 22, 2005 @author

    super (name);
  }


  public void testFromSerialization () throws IOException, ClassNotFoundException
  {
    Pipe p = new GenericAcrfData2TokenSequence ();
    InstanceList training = new InstanceList (p);
    training.addThruPipe (new LineGroupIterator (new StringReader (sampleData), Pattern.compile ("^$"), true));


    Pipe p2 = (Pipe) TestSerializable.cloneViaSerialization (p);


    InstanceList l1 = new InstanceList (p);
    l1.addThruPipe (new LineGroupIterator (new StringReader (sampleData2), Pattern.compile ("^$"), true));
    InstanceList l2 = new InstanceList (p2);
    l2.addThruPipe (new LineGroupIterator (new StringReader (sampleData2), Pattern.compile ("^$"), true));


    // the readResolve alphabet thing doesn't kick in on first deserialization
    assertTrue (p.getTargetAlphabet () != p2.getTargetAlphabet ());


    assertEquals (1, l1.size ());
    assertEquals (1, l2.size ());


    Instance inst1 = l1.get (0);

View Full Code Here

    }
  }


  public void testFixedNumLabels () throws IOException, ClassNotFoundException
  {
    Pipe p = new GenericAcrfData2TokenSequence (2);
    InstanceList training = new InstanceList (p);
    training.addThruPipe (new LineGroupIterator (new StringReader (sampleFixedData), Pattern.compile ("^$"), true));


    assertEquals (1, training.size ());

View Full Code Here

    assertEquals (4, ls1.size ());
  }


  public void testLabelsAtEnd () throws IOException, ClassNotFoundException
  {
    GenericAcrfData2TokenSequence p = new GenericAcrfData2TokenSequence (2);
    p.setLabelsAtEnd (true);


    InstanceList training = new InstanceList (p);
    training.addThruPipe (new LineGroupIterator (new StringReader (labelsAtEndData), Pattern.compile ("^$"), true));


    assertEquals (1, training.size ());


    Instance inst1 = training.get (0);
    StringTokenization toks = (StringTokenization) inst1.getData ();
    LabelsSequence ls1 = (LabelsSequence) inst1.getTarget ();


    assertEquals (4, ls1.size ());
    assertEquals (3, toks.get(0).getFeatures ().size ());
    assertEquals ("LBLB LBLD", ls1.getLabels (0).toString ());


    LabelAlphabet globalDict = p.getLabelAlphabet (0);
    assertEquals (2, p.numLevels ());
    assertEquals (globalDict, ls1.getLabels (0).get (0).getLabelAlphabet ());
  }

View Full Code Here

    assertEquals (globalDict, ls1.getLabels (0).get (0).getLabelAlphabet ());
  }


  public void testNoTokenText ()
  {
    GenericAcrfData2TokenSequence p = new GenericAcrfData2TokenSequence (2);
    p.setFeaturesIncludeToken(false);
    p.setIncludeTokenText(false);


    InstanceList training = new InstanceList (p);
    training.addThruPipe (new LineGroupIterator (new StringReader (sampleFixedData), Pattern.compile ("^$"), true));


    assertEquals (1, training.size ());

View Full Code Here

    File trainFile = new File (args[0]);
    File testFile = new File (args[1]);
    File crfFile = new File (args[2]);


    Pipe pipe = new SerialPipes (new Pipe[] {
        new GenericAcrfData2TokenSequence (2),
        new TokenSequence2FeatureVectorSequence (true, true),
    });


    InstanceList training = new InstanceList (pipe);
    training.addThruPipe (new LineGroupIterator (new FileReader (trainFile),

View Full Code Here

TOP

Examples of cc.mallet.grmm.learning.GenericAcrfData2TokenSequence

Related Classes of cc.mallet.grmm.learning.GenericAcrfData2TokenSequence