本文整理汇总了Java中edu.umass.cs.mallet.base.pipe.tsf.OffsetConjunctions类的典型用法代码示例。如果您正苦于以下问题：Java OffsetConjunctions类的具体用法？Java OffsetConjunctions怎么用？Java OffsetConjunctions使用的例子？那么恭喜您, 这里精选的类代码示例或许可以为您提供帮助。
OffsetConjunctions类属于edu.umass.cs.mallet.base.pipe.tsf包，在下文中一共展示了OffsetConjunctions类的3个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Java代码示例。
示例1: makeSpacePredictionPipe
import edu.umass.cs.mallet.base.pipe.tsf.OffsetConjunctions; //导入依赖的package包/类
public static Pipe makeSpacePredictionPipe ()
{
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},
//{-3,-2,-1}, {-2,-1,0}, {-1,0,1}, {0,1,2}, {1,2,3},
}),
// new PrintInputAndTarget(),
new TokenSequence2FeatureVectorSequence()
});
return p;
}
示例2: setupPipes
import edu.umass.cs.mallet.base.pipe.tsf.OffsetConjunctions; //导入依赖的package包/类
private static void setupPipes(ArrayList<Pipe> pipes, String regexFilename)
{
try
{
if (regexFilename != null)
pipes.add(new ConfigurableRegexMatches(regexFilename));
} catch (IOException e)
{
throw new RuntimeException(e);
}
pipes.add(new TokenTextCharPrefix("2PREFIX=", 2));
pipes.add(new TokenTextCharPrefix("3PREFIX=", 3));
pipes.add(new TokenTextCharPrefix("4PREFIX=", 4));
pipes.add(new TokenTextCharSuffix("2SUFFIX=", 2));
pipes.add(new TokenTextCharSuffix("3SUFFIX=", 3));
pipes.add(new TokenTextCharSuffix("4SUFFIX=", 4));
pipes.add(new TokenTextCharNGrams("CHARNGRAM=", new int[] { 2, 3 }, true));
// pipes.add(new LexiconMembership()); // Use this for determining
// whether word in a lexicon
pipes.add(new RegexMatches("ROMAN", Pattern.compile("[IVXDLCM]+", Pattern.CASE_INSENSITIVE)));
pipes.add(new RegexMatches("GREEK", Pattern.compile(GREEK, Pattern.CASE_INSENSITIVE)));
pipes.add(new RegexMatches("ISPUNCT", Pattern.compile("[`[email protected]#$%^&*()-=_+\\[\\]\\\\{}|;\':\\\",./<>?]+")));
pipes.add(new OffsetConjunctions(new int[][] { { -2 }, { -1 }, { 1 }, { 2 } }));
pipes.add(new TokenSequence2FeatureVectorSequence(true, true));
}
示例3: setupPipes
import edu.umass.cs.mallet.base.pipe.tsf.OffsetConjunctions; //导入依赖的package包/类
private static void setupPipes(ArrayList<Pipe> pipes)
{
pipes.add(new RegexMatches("ALPHA", Pattern.compile("[A-Za-z]+")));
pipes.add(new RegexMatches("INITCAPS", Pattern.compile("[A-Z].*")));
pipes.add(new RegexMatches("UPPER-LOWER", Pattern.compile("[A-Z][a-z].*")));
pipes.add(new RegexMatches("LOWER-UPPER", Pattern.compile("[a-z]+[A-Z]+.*")));
pipes.add(new RegexMatches("ALLCAPS", Pattern.compile("[A-Z]+")));
pipes.add(new RegexMatches("MIXEDCAPS", Pattern.compile("[A-Z][a-z]+[A-Z][A-Za-z]*")));
pipes.add(new RegexMatches("SINGLECHAR", Pattern.compile("[A-Za-z]")));
pipes.add(new RegexMatches("SINGLEDIGIT", Pattern.compile("[0-9]")));
pipes.add(new RegexMatches("DOUBLEDIGIT", Pattern.compile("[0-9][0-9]")));
pipes.add(new RegexMatches("NUMBER", Pattern.compile("[0-9,]+")));
pipes.add(new RegexMatches("HASDIGIT", Pattern.compile(".*[0-9].*")));
pipes.add(new RegexMatches("ALPHANUMERIC", Pattern.compile(".*[0-9].*[A-Za-z].*")));
pipes.add(new RegexMatches("ALPHANUMERIC", Pattern.compile(".*[A-Za-z].*[0-9].*")));
pipes.add(new RegexMatches("LETTERS_NUMBERS", Pattern.compile("[0-9]+[A-Za-z]+")));
pipes.add(new RegexMatches("NUMBERS_LETTERS", Pattern.compile("[A-Za-z]+[0-9]+")));
pipes.add(new RegexMatches("HAS_DASH", Pattern.compile(".*-.*")));
pipes.add(new RegexMatches("HAS_QUOTE", Pattern.compile(".*'.*")));
pipes.add(new RegexMatches("HAS_SLASH", Pattern.compile(".*/.*")));
// Start second set of new features (to handle improvements in
// BaseTokenizer)
pipes.add(new RegexMatches("REALNUMBER", Pattern.compile("(-|\\+)?[0-9,]+(\\.[0-9]*)?%?")));
pipes.add(new RegexMatches("REALNUMBER", Pattern.compile("(-|\\+)?[0-9,]*(\\.[0-9]+)?%?")));
pipes.add(new RegexMatches("START_MINUS", Pattern.compile("-.*")));
pipes.add(new RegexMatches("START_PLUS", Pattern.compile("\\+.*")));
pipes.add(new RegexMatches("END_PERCENT", Pattern.compile(".*%")));
// End second set
pipes.add(new TokenTextCharPrefix("2PREFIX=", 2));
pipes.add(new TokenTextCharPrefix("3PREFIX=", 3));
pipes.add(new TokenTextCharPrefix("4PREFIX=", 4));
pipes.add(new TokenTextCharSuffix("2SUFFIX=", 2));
pipes.add(new TokenTextCharSuffix("3SUFFIX=", 3));
pipes.add(new TokenTextCharSuffix("4SUFFIX=", 4));
pipes.add(new TokenTextCharNGrams("CHARNGRAM=", new int[] {2, 3}, true));
// pipes.add(new LexiconMembership()); // Use this for determining
// whether word in a lexicon
pipes.add(new RegexMatches("ROMAN", Pattern.compile("[IVXDLCM]+", Pattern.CASE_INSENSITIVE)));
pipes.add(new RegexMatches("GREEK", Pattern.compile(GREEK, Pattern.CASE_INSENSITIVE)));
pipes.add(new RegexMatches("ISPUNCT", Pattern.compile("[`[email protected]#$%^&*()-=_+\\[\\]\\\\{}|;\':\\\",./<>?]+")));
pipes.add(new OffsetConjunctions(new int[][] { {-2}, {2}}));
pipes.add(new TokenSequence2FeatureVectorSequence(true, true));
}