com.hankcs.hanlp.model.hmm

类 SecondOrderHiddenMarkovModel

java.lang.Object

com.hankcs.hanlp.model.hmm.HiddenMarkovModel

com.hankcs.hanlp.model.hmm.SecondOrderHiddenMarkovModel

public class SecondOrderHiddenMarkovModel
extends HiddenMarkovModel

作者:

hankcs

构造器概要

构造器

构造器和说明
SecondOrderHiddenMarkovModel()
SecondOrderHiddenMarkovModel(float[] start_probability, float[][] transition_probability, float[][] emission_probability, float[][][] transition_probability2)

方法概要

限定符和类型	方法和说明
protected void	estimateTransitionProbability(Collection<int[][]> samples, int max_state) 利用极大似然估计转移概率
int[][]	generate(int length) 生成样本序列
float	predict(int[] observation, int[] state) 预测（维特比算法）
boolean	similar(HiddenMarkovModel model)
protected void	toLog()
void	unLog()

从类继承的方法 com.hankcs.hanlp.model.hmm.HiddenMarkovModel

drawFrom, estimateEmissionProbability, estimateStartProbability, generate, logToCdf, logToCdf, normalize, predict, similar, train

从类继承的方法 java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

构造器详细资料

SecondOrderHiddenMarkovModel

public SecondOrderHiddenMarkovModel(float[] start_probability,
                                    float[][] transition_probability,
                                    float[][] emission_probability,
                                    float[][][] transition_probability2)

SecondOrderHiddenMarkovModel

public SecondOrderHiddenMarkovModel()

方法详细资料

estimateTransitionProbability

protected void estimateTransitionProbability(Collection<int[][]> samples,
                                             int max_state)

从类复制的说明: HiddenMarkovModel

利用极大似然估计转移概率

覆盖:

estimateTransitionProbability 在类中 HiddenMarkovModel

参数:

samples - 训练样本集

max_state - 状态的最大下标，等于N-1

generate

public int[][] generate(int length)

从类复制的说明: HiddenMarkovModel

生成样本序列

指定者:

generate 在类中 HiddenMarkovModel

参数:

length - 序列长度

返回:

序列

toLog

protected void toLog()

覆盖:

toLog 在类中 HiddenMarkovModel

predict

public float predict(int[] observation,
                     int[] state)

从类复制的说明: HiddenMarkovModel

预测（维特比算法）

指定者:

predict 在类中 HiddenMarkovModel

参数:

observation - 观测序列

state - 预测状态序列（需预先分配内存）

返回:

概率的对数，可利用 (float) Math.exp(maxScore) 还原

unLog

public void unLog()

覆盖:

unLog 在类中 HiddenMarkovModel

similar

public boolean similar(HiddenMarkovModel model)

覆盖:

similar 在类中 HiddenMarkovModel