Package cc.mallet.pipe.tsf

Examples of cc.mallet.pipe.tsf.TokenText


  private Pipe makeSpacePredictionPipe() {
    Pipe p = new SerialPipes(new Pipe[] {
        new CharSequence2TokenSequence("."),
        new TokenSequenceLowercase(),
        new TestCRFTokenSequenceRemoveSpaces(),
        new TokenText(),
        new OffsetConjunctions(true, new int[][] { { 0 }, { 1 },
            { -1, 0 },

        // Original test had this conjunction in it too
            // {1},{-1,0},{0,1},
View Full Code Here


  }

  public void testPrint() {
    Pipe p = new SerialPipes(new Pipe[] {
        new CharSequence2TokenSequence("."), new TokenText(),
        new TestCRFTokenSequenceRemoveSpaces(),
        new TokenSequence2FeatureVectorSequence(),
        new PrintInputAndTarget(), });
    InstanceList one = new InstanceList(p);
    String[] data = new String[] { "ABCDE", };
View Full Code Here

    crf.print();
  }

  public void testCopyStatesAndWeights() {
    Pipe p = new SerialPipes(new Pipe[] {
        new CharSequence2TokenSequence("."), new TokenText(),
        new TestCRFTokenSequenceRemoveSpaces(),
        new TokenSequence2FeatureVectorSequence(),
        new PrintInputAndTarget(), });
    InstanceList one = new InstanceList(p);
    String[] data = new String[] { "ABCDE", };
View Full Code Here

  public void testStartState() {
    Pipe p = new SerialPipes(new Pipe[] {
        new LineGroupString2TokenSequence(),
        new TokenSequenceMatchDataAndTarget(Pattern
            .compile("^(\\S+) (.*)"), 2, 1),
        new TokenSequenceParseFeatureString(false), new TokenText(),
        new TokenSequence2FeatureVectorSequence(true, false),
        new Target2LabelSequence(), new PrintInputAndTarget(), });

    InstanceList data = new InstanceList(p);
    data.addThruPipe(new LineGroupIterator(new StringReader(toy), Pattern
View Full Code Here

  public static void testMultiTag ()
  {
    Pipe mtPipe = new SerialPipes (new Pipe[] {
            new SimpleTaggerSentence2TokenSequence (),
            new TokenText (),
            new RegexMatches ("digits", Pattern.compile ("[0-9]+")),
            new RegexMatches ("ampm", Pattern.compile ("[aApP][mM]")),
            new OffsetFeatureConjunction ("time",
                    new String[] { "digits", "ampm" },
                    new int[] { 0, 1 },
                    true),
            new PrintInputAndTarget (),
    });
    Pipe noMtPipe = new SerialPipes (new Pipe[] {
            new SimpleTaggerSentence2TokenSequence (),
            new TokenText (),
            new RegexMatches ("digits", Pattern.compile ("[0-9]+")),
            new RegexMatches ("ampm", Pattern.compile ("[aApP][mM]")),
            new OffsetFeatureConjunction ("time",
                    new String[] { "digits", "ampm" },
                    new int[] { 0, 1 },
View Full Code Here

  public static void testMultiTagSerialization () throws IOException, ClassNotFoundException
  {
    Pipe origPipe = new SerialPipes (new Pipe[] {
            new SimpleTaggerSentence2TokenSequence (),
            new TokenText (),
            new RegexMatches ("digits", Pattern.compile ("[0-9]+")),
            new RegexMatches ("ampm", Pattern.compile ("[aApP][mM]")),
            new OffsetFeatureConjunction ("time",
                    new String[] { "digits", "ampm" },
                    new int[] { 0, 1 },
View Full Code Here

  {
    Pipe p = new SerialPipes(new Pipe[]{
      new CharSequence2TokenSequence("."),
      new TokenSequenceLowercase(),
      new TestMEMMTokenSequenceRemoveSpaces(),
      new TokenText(),
      new OffsetConjunctions(true,
                             new int[][]{//{0}, /*{1},{-1,0},{0,1}, */
                               {1}, {-1, 0}, {0, 1},
//                               {-2, -1, 0}, {0, 1, 2}, {-3, -2, -1}, {1, 2, 3},
                               //{-2,-1}, {-1,0}, {0,1}, {1,2},
View Full Code Here

  public void disabledtestPrint ()
  {
    Pipe p = new SerialPipes (new Pipe[] {
       new CharSequence2TokenSequence("."),
       new TokenText(),
       new TestMEMM.TestMEMMTokenSequenceRemoveSpaces(),
       new TokenSequence2FeatureVectorSequence(),
       new PrintInputAndTarget(),
    });
    InstanceList one = new InstanceList (p);
View Full Code Here

TOP

Related Classes of cc.mallet.pipe.tsf.TokenText

Copyright © 2018 www.massapicom. All rights reserved.
All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.