Java 实现测字功能时出现的问题（使用stanford词性标记器进行词性标记）

我发现每个令牌的POS标签频率，例如（Np、JJ..）。如何查找POS标记的bigrams和trigrams分布？（我正在使用stanford POS tagger java I.e） Unigram的代码为

MaxentTagger tagger = new MaxentTagger("taggers/english-left3words-distsim.tagger");

// The sample string
String sample = "This is a sample text";

// The tagged string
String tagged = tagger.tagString(s);
final String tagged = s;
int nouns = 0;
int adjectives = 0;
int adverbs = 0;
int verbs = 0;
int cd = 0;  // Cardinal number
int preposition = 0;
int fw = 0;
int particle = 0;
int symbol = 0;
int conjuction = 0;
int Determiner = 0;
int interrogative = 0;
int prp$ = 0; //Possessive pronoun
final String[] tokens = tagged.split(" ");

for (final String token : tokens) {
    //System.out.println(token);
    final int lastUnderscoreIndex = token.lastIndexOf("_");
    final String realToken = token.substring(lastUnderscoreIndex + 1);
    if ("NN".equals(realToken) || "NNS".equals(realToken) || "NNP".equals(realToken) || "NNPS".equals(realToken)) {
        nouns++;
    }
    if ("JJ".equals(realToken) || "JJR".equals(realToken) || "JJR".equals(realToken)) {
        adjectives++;
    }
    if ("RB".equals(realToken) || "RBS".equals(realToken) || "RBR".equals(realToken)) {
        adverbs++;
    }
    if ("VB".equals(realToken) || "VBD".equals(realToken) || "VBG".equals(realToken)
            || "VBN".equals(realToken) || "VBP".equals(realToken) || "VBZ".equals(realToken)) {
        verbs++;
    }
    if ("CD".equals(realToken)) {
        cd++;
    }
    if ("IN".equals(realToken) || "TO".equals(realToken)) {
        preposition++;
    }
    if ("RP".equals(realToken)) {
        particle++;
    }
    if ("SYM".equals(realToken)) {
        symbol++;
    }
    if ("CC".equals(realToken)) {
        conjuction++;
    }
    if ("DT".equals(realToken)) {
        Determiner++;
    }
    if ("WDT".equals(realToken) || "WP".equals(realToken) || "WRB".equals(realToken)) {

        interrogative++;
    }
    if ("FW".equals(realToken)) {
        fw++;
    }
    if ("PRP$".equals(realToken)) {
        prp$++;
    }
}