Apache OpenNLP的初探

https://blog.csdn.net/Richard_vi/article/details/78909939?utm_medium=distribute.pc_relevant.none-task-blog-2%7Edefault%7EBlogCommendFromBaidu%7Edefault-5.control&depth_1-utm_source=distribute.pc_relevant.none-task-blog-2%7Edefault%7EBlogCommendFromBaidu%7Edefault-5.control

 

 

环境：IDEA+jdk8+maven 3.5.2
新建maven项目，添加nlp的maven依赖：

<dependency>
<groupId>org.apache.opennlp</groupId>
<artifactId>opennlp-tools</artifactId>
<version>1.8.4</version>
</dependency>

然后就可以使用nlp的开发工具了。我们来看一些实例：

    //divide sentences
    public static void SentenceDetect() throws IOException {
        String paragraph = "Hi. How are you? This is JD_Dog. He is my good friends.He is very kind.but he is no more handsome than me. ";
        InputStream is = new FileInputStream("E:\\NLP_Practics\\models\\en-sent.bin");
        SentenceModel model = new SentenceModel(is);
        SentenceDetectorME sdetector = new SentenceDetectorME(model);
        String sentences[] = sdetector.sentDetect(paragraph);
        for (String single : sentences) {
            System.out.println(single);
        }
        is.close();
    }

　　

这是一个英文分词的实例，我们首先要去下载英文分词的模型，在这里，我将它放到了E:\NLP_Practics\models\目录下。
关于更多模型的下载可以在地址：
http://maven.tamingtext.com/opennlp-models/models-1.5/
中找到。
我们来看下对应的输出结果：

Hi. How are you?
This is JD_Dog.
He is my good friends.He is very kind.but he is no more handsome than me.

　　是不是很神奇呢？哈哈哈也没什么可神奇的。这里只是使用现有的一个简单模型做了一个示范，模型是从大量的训练数据中具象出来的，因此分析的结果好坏还要取决于你使用的模型。
我们再看一个英文分词的例子：

//devide words
    public static void Tokenize() throws IOException {
        InputStream is = new FileInputStream("E:\\NLP_Practics\\models\\en-token.bin");
        TokenizerModel model = new TokenizerModel(is);
        Tokenizer tokenizer = new TokenizerME(model);
        String tokens[] = tokenizer.tokenize("Hi. How are you? This is Richard. Richard is still single. please help him find his girl");
        for (String a : tokens)
            System.out.println(a);
        is.close();
    }

　　运行结果：

Hi
.
How
are
you
?
This
is
Richard
.
Richard
is
still
single
.
please
help
him
find
his
girl

　　

 

完整测试代码：

package package01;

import opennlp.tools.sentdetect.SentenceDetectorME;
import opennlp.tools.sentdetect.SentenceModel;
import opennlp.tools.tokenize.Tokenizer;
import opennlp.tools.tokenize.TokenizerME;
import opennlp.tools.tokenize.TokenizerModel;

import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;

public class Test01 {

    //divide sentences
    public static void SentenceDetect() throws IOException {
        String paragraph = "Hi. How are you? This is JD_Dog. He is my good friends.He is very kind.but he is no more handsome than me. ";
        InputStream is = new FileInputStream("E:\\NLP_Practics\\models\\en-sent.bin");
        SentenceModel model = new SentenceModel(is);
        SentenceDetectorME sdetector = new SentenceDetectorME(model);
        String sentences[] = sdetector.sentDetect(paragraph);
        for (String single : sentences) {
            System.out.println(single);
        }
        is.close();
    }

    //devide words
    public static void Tokenize() throws IOException {
        InputStream is = new FileInputStream("E:\\NLP_Practics\\models\\en-token.bin");
        TokenizerModel model = new TokenizerModel(is);
        Tokenizer tokenizer = new TokenizerME(model);
        String tokens[] = tokenizer.tokenize("Hi. How are you? This is Richard. Richard is still single. please help him find his girl");
        for (String a : tokens)
            System.out.println(a);
        is.close();
    }

    public static void main(String[] args) throws IOException {
//        Test01.SentenceDetect();
        Test01.Tokenize();
    }

}