Package org.fnlp.nlp.cn.tag

Examples of org.fnlp.nlp.cn.tag.POSTagger

200
201
202
203
204
205
206
207
208
209
210
  public static void loadTag(String path) throws LoadModelException {
    if(pos==null){

      String file = path+posModel;
      if(seg==null)
        pos = new POSTagger(file);
      else{
        pos = new POSTagger(seg,file);         
      }
    }
  }
View Full Code Here
48
49
50
51
52
53
54
55
56
57
58
59
  /**
   * 只输入句子，不带词性
   * @throws Exception
   */
  private static void test(String word) throws Exception {   
    POSTagger tag = new POSTagger("../models/seg.m","../models/pos.m");
    String[][] s = tag.tag2Array(word);
    try {
      DependencyTree tree = parser.parse2T(s[0],s[1]);
      System.out.println(tree.toString());
      String stree = parser.parse2String(s[0],s[1],true);
      System.out.println(stree);
View Full Code Here
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
   */
  public static void main(String[] args) throws Exception {

   
    CWSTagger cws = new CWSTagger("../models/seg.m");
    tag = new POSTagger(cws,"../models/pos.m");
   
    System.out.println("得到支持的词性标签集合");
    System.out.println(tag.getSupportedTags());
    System.out.println(tag.getSupportedTags().size());
    System.out.println("\n");
   
    String str = "媒体计算研究所成立了，高级数据挖掘很难。乐phone很好！";
    String s = tag.tag(str);
    System.out.println("处理未分词的句子");
    System.out.println(s);
   
    System.out.println("使用英文标签");
    tag.SetTagType("en");   
    System.out.println(tag.getSupportedTags());
    System.out.println(tag.getSupportedTags().size());
    s = tag.tag(str);
    System.out.println(s);   
    System.out.println();
   
    CWSTagger cws2 = new CWSTagger("../models/seg.m", new Dictionary("../models/dict.txt"));
   
    //bool值指定该dict是否用于cws分词（分词和词性可以使用不同的词典）
    tag = new POSTagger(cws2, "../models/pos.m"
        , new Dictionary("../models/dict.txt"), true);//true就替换了之前的dict.txt
    tag.removeDictionary(false);//不移除分词的词典
    tag.setDictionary(new Dictionary("../models/dict.txt"), false);//设置POS词典，分词使用原来设置
   
    String str2 = "媒体计算研究所成立了，高级数据挖掘很难。乐phone很好！";
    String s2 = tag.tag(str2);
    System.out.println("处理未分词的句子，使用词典");
    System.out.println(s2);
    System.out.println();
   
    Dictionary dict = new Dictionary();
    dict.add("媒体计算","mypos1","mypos2");
    dict.add("乐phone","专有名");
    tag.setDictionary(dict, true);
    String s22 = tag.tag(str2);
    System.out.println(s22);
    System.out.println();
   
    POSTagger tag1 = new POSTagger("../models/pos.m");
    String str1 = "媒体计算 研究所 成立 了 , 高级 数据挖掘 很 难";
    String[] w = str1.split(" ");
    String[] s1 = tag1.tagSeged(w);
    System.out.println("直接处理分好词的句子:++++++++++");
    for(int i=0;i<s1.length;i++){
      System.out.print(w[i]+"/"+s1[i]+" ");
    }
    System.out.println("\n");
   
    POSTagger tag3 = new POSTagger("../models/pos.m", new Dictionary("../models/dict.txt"));
    String str3 = "媒体计算 研究所 成立 了 , 高级 数据挖掘 很 难 ";
    String[] w3 = str3.split(" ");
    String[] s3 = tag3.tagSeged(w3);
    System.out.println("直接处理分好词的句子，使用词典");
    for(int i=0;i<s3.length;i++){
      System.out.print(w3[i]+"/"+s3[i]+" ");
    }
    System.out.println("\n");
   
    //????????????????????????????
   
    System.out.println("重新构造");
    cws = new CWSTagger("../models/seg.m");
    tag = new POSTagger(cws,"../models/pos.m");
    str = "媒体计算研究所成立了, 高级数据挖掘很难";
    System.out.println(tag.tag(str));
    String[][] sa = tag.tag2Array(str);
    for(int i = 0; i < sa.length; i++) {
      for(int j = 0; j < sa[i].length; j++) {
View Full Code Here
48
49
50
51
52
53
54
55
56
    ep = new EntitiesGetter();   
    cl = Linear.loadFrom(armodel);
  }
 
  public Anaphora(String segmodel, String posmodel, String armodel) throws LoadModelException{
    pos = new POSTagger(segmodel,posmodel);
    ep = new EntitiesGetter();   
    cl = Linear.loadFrom(armodel);
  }
View Full Code Here
40
41
42
43
44
45
46
47
  public RuleAnaphora() throws Exception{ 
    ep = new EntitiesGetter(); 
  }
 
  public RuleAnaphora(String segmodel, String posmodel) throws Exception{
    pos = new POSTagger(segmodel,posmodel);
    ep = new EntitiesGetter(); 
  }
View Full Code Here
90
91
92
93
94
95
96
97
98
99
100
  public LinkedList<Instance> getLlist(){
    return this.llist;
   
  }
  public static void main(String args[]) throws Exception{
    FileGroupReader.tag = new POSTagger("../models/seg.m", "../models/pos.m");
   
    MyDocumentWriter dr1 = new MyDocumentWriter("../tmp/ar");
    dr1.writeOut("../tmp/ar-train.txt");
    System.out.print("已经写入文档");
  }
View Full Code Here
55
56
57
58
59
60
61
62
63
64
65
    System.out.print("Done");
  }

  public void addEnTag(String file) throws LoadModelException,
      IOException {
    AbstractTagger cl = new POSTagger(file);
     

    addEnTag(cl,file);
    cl.saveTo(file);
  }
View Full Code Here
37
38
39
40
41
42
43
44
45
46
47
   * @param args
   * @throws Exception
   */
  public static void main(String[] args) throws Exception {
    CWSTagger seg = new CWSTagger("./models/seg.m"); 
    POSTagger pos = new POSTagger(seg, "./models/pos.m");

    RLSeg rlseg = new RLSeg(seg,"./tmpdata/FNLPDATA/all.dict");
//    tag.setDictionary(rlseg.tempdict);
    String file = "./tmpdata/20120927-微博分词-5000-test-utf-8.txt";
    BufferedReader bfr = new BufferedReader(new InputStreamReader(new FileInputStream(file),"utf8"));
View Full Code Here
39
40
41
42
43
44
45
46
47
48
   * @param args
   * @throws Exception
   */
  public static void main(String[] args) throws Exception {
    parser = new JointParser("../models/dep.m");
    tag = new POSTagger("../models/seg.m","../models/pos.m");

    test();

  }
View Full Code Here
39
40
41
42
43
44
45
46
47
48
49
   * @throws IOException
   * @throws 
   */
  public static void main(String[] args) throws Exception {
    // TODO Auto-generated method stub
    tag = new POSTagger("models/seg.m","models/pos.m");
   
    ArrayList<String> str = MyCollection.loadList("./testcase/test case pos.txt",null);
    str.add("周杰伦 生 于 台湾\n我们");
    str.add("分析和比较");
   
View Full Code Here
TOP

Related Classes of org.fnlp.nlp.cn.tag.POSTagger

  • org.apache.commons.cli.BasicParser
  • org.apache.commons.cli.CommandLine
  • org.apache.commons.cli.HelpFormatter
  • org.apache.commons.cli.Options
  • org.fnlp.demo.nlp.DepParser
  • org.fnlp.demo.nlp.PartsOfSpeechTag
  • org.fnlp.ml.classifier.struct.inf.ConstraintViterbi
  • org.fnlp.ml.classifier.struct.inf.LinearViterbi
  • org.fnlp.ml.types.Instance
  • org.fnlp.nlp.cn.anaphora.Anaphora
    • 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.