Package edu.berkeley.nlp.lm
Class NgramLanguageModel.StaticMethods
- java.lang.Object
-
- edu.berkeley.nlp.lm.NgramLanguageModel.StaticMethods
-
- Enclosing interface:
- NgramLanguageModel<W>
public static class NgramLanguageModel.StaticMethods extends java.lang.Object
-
-
Constructor Summary
Constructors Constructor Description StaticMethods()
-
Method Summary
All Methods Static Methods Concrete Methods Modifier and Type Method Description static <W> Counter<W>
getDistributionOverNextWords(NgramLanguageModel<W> lm, java.util.List<W> context)
Builds a distribution over next possible words given the context.static <W> java.util.List<W>
sample(java.util.Random random, NgramLanguageModel<W> lm)
Samples from this language model.static <W> java.util.List<W>
sample(java.util.Random random, NgramLanguageModel<W> lm, double sampleTemperature)
static <T> int[]
toIntArray(java.util.List<T> ngram, ArrayEncodedNgramLanguageModel<T> lm)
static <T> java.util.List<T>
toObjectList(int[] ngram, ArrayEncodedNgramLanguageModel<T> lm)
-
-
-
Method Detail
-
toIntArray
public static <T> int[] toIntArray(java.util.List<T> ngram, ArrayEncodedNgramLanguageModel<T> lm)
-
toObjectList
public static <T> java.util.List<T> toObjectList(int[] ngram, ArrayEncodedNgramLanguageModel<T> lm)
-
sample
public static <W> java.util.List<W> sample(java.util.Random random, NgramLanguageModel<W> lm)
Samples from this language model. This is not meant to be particularly efficient- Parameters:
random
-- Returns:
-
sample
public static <W> java.util.List<W> sample(java.util.Random random, NgramLanguageModel<W> lm, double sampleTemperature)
-
getDistributionOverNextWords
public static <W> Counter<W> getDistributionOverNextWords(NgramLanguageModel<W> lm, java.util.List<W> context)
Builds a distribution over next possible words given the context. Context can be of any length, but only at mostlm.getLmOrder() - 1
words are actually used.- Type Parameters:
W
-- Parameters:
lm
-context
-- Returns:
-
-