18

我想 POSTag 一个英文句子并做一些处理。我想使用openNLP。我已经安装了

当我执行命令时

I:\Workshop\Programming\nlp\opennlp-tools-1.5.0-bin\opennlp-tools-1.5.0>java -jar opennlp-tools-1.5.0.jar POSTagger models\en-pos-maxent.bin < Text.txt

它在 Text.txt 中给出输出 POSTagging 输入

    Loading POS Tagger model ... done (4.009s)
My_PRP$ name_NN is_VBZ Shabab_NNP i_FW am_VBP 22_CD years_NNS old._.


Average: 66.7 sent/s
Total: 1 sent
Runtime: 0.015s

我希望它安装正确?

现在我如何从 Java 应用程序内部进行此 POSTtagging?我已将 openNLPtools、jwnl、maxent jar 添加到项目中,但如何调用 POSTtagging?

4

3 回答 3

40

这是我放在一起的一些(旧)示例代码,后面是现代化的代码:

package opennlp;

import opennlp.tools.cmdline.PerformanceMonitor;
import opennlp.tools.cmdline.postag.POSModelLoader;
import opennlp.tools.postag.POSModel;
import opennlp.tools.postag.POSSample;
import opennlp.tools.postag.POSTaggerME;
import opennlp.tools.tokenize.WhitespaceTokenizer;
import opennlp.tools.util.ObjectStream;
import opennlp.tools.util.PlainTextByLineStream;

import java.io.File;
import java.io.IOException;
import java.io.StringReader;

public class OpenNlpTest {
public static void main(String[] args) throws IOException {
    POSModel model = new POSModelLoader().load(new File("en-pos-maxent.bin"));
    PerformanceMonitor perfMon = new PerformanceMonitor(System.err, "sent");
    POSTaggerME tagger = new POSTaggerME(model);

    String input = "Can anyone help me dig through OpenNLP's horrible documentation?";
    ObjectStream<String> lineStream =
            new PlainTextByLineStream(new StringReader(input));

    perfMon.start();
    String line;
    while ((line = lineStream.read()) != null) {

        String whitespaceTokenizerLine[] = WhitespaceTokenizer.INSTANCE.tokenize(line);
        String[] tags = tagger.tag(whitespaceTokenizerLine);

        POSSample sample = new POSSample(whitespaceTokenizerLine, tags);
        System.out.println(sample.toString());

        perfMon.incrementCounter();
    }
    perfMon.stopAndPrintFinalResult();
}
}

输出是:

Loading POS Tagger model ... done (2.045s)
Can_MD anyone_NN help_VB me_PRP dig_VB through_IN OpenNLP's_NNP horrible_JJ documentation?_NN

Average: 76.9 sent/s 
Total: 1 sent
Runtime: 0.013s

这基本上是从作为 OpenNLP 的一部分包含的 POSTaggerTool 类中工作的。sample.getTags()是一个String具有标签类型本身的数组。

这需要对训练数据的直接文件访问,这真的非常糟糕。

更新后的代码库有点不同(可能更有用。)

首先,一个 Maven POM:

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>

    <groupId>org.javachannel</groupId>
    <artifactId>opennlp-example</artifactId>
    <version>1.0-SNAPSHOT</version>
    <dependencies>
        <dependency>
            <groupId>org.apache.opennlp</groupId>
            <artifactId>opennlp-tools</artifactId>
            <version>1.6.0</version>
        </dependency>
        <dependency>
            <groupId>org.testng</groupId>
            <artifactId>testng</artifactId>
            <version>[6.8.21,)</version>
            <scope>test</scope>
        </dependency>
    </dependencies>
    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <version>3.1</version>
                <configuration>
                    <source>1.8</source>
                    <target>1.8</target>
                </configuration>
            </plugin>
        </plugins>
    </build>
</project>

这是作为测试编写的代码,因此位于./src/test/java/org/javachannel/opennlp/example

package org.javachannel.opennlp.example;

import opennlp.tools.cmdline.PerformanceMonitor;
import opennlp.tools.postag.POSModel;
import opennlp.tools.postag.POSSample;
import opennlp.tools.postag.POSTaggerME;
import opennlp.tools.tokenize.WhitespaceTokenizer;
import org.testng.annotations.DataProvider;
import org.testng.annotations.Test;

import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.net.URL;
import java.nio.channels.Channels;
import java.nio.channels.ReadableByteChannel;
import java.util.stream.Stream;

public class POSTest {
    private void download(String url, File destination) throws IOException {
        URL website = new URL(url);
        ReadableByteChannel rbc = Channels.newChannel(website.openStream());
        FileOutputStream fos = new FileOutputStream(destination);
        fos.getChannel().transferFrom(rbc, 0, Long.MAX_VALUE);
    }

    @DataProvider
    Object[][] getCorpusData() {
        return new Object[][][]{{{
                "Can anyone help me dig through OpenNLP's horrible documentation?"
        }}};
    }

    @Test(dataProvider = "getCorpusData")
    public void showPOS(Object[] input) throws IOException {
        File modelFile = new File("en-pos-maxent.bin");
        if (!modelFile.exists()) {
            System.out.println("Downloading model.");
            download("http://opennlp.sourceforge.net/models-1.5/en-pos-maxent.bin", modelFile);
        }
        POSModel model = new POSModel(modelFile);
        PerformanceMonitor perfMon = new PerformanceMonitor(System.err, "sent");
        POSTaggerME tagger = new POSTaggerME(model);

        perfMon.start();
        Stream.of(input).map(line -> {
            String whitespaceTokenizerLine[] = WhitespaceTokenizer.INSTANCE.tokenize(line.toString());
            String[] tags = tagger.tag(whitespaceTokenizerLine);

            POSSample sample = new POSSample(whitespaceTokenizerLine, tags);

            perfMon.incrementCounter();
            return sample.toString();
        }).forEach(System.out::println);
        perfMon.stopAndPrintFinalResult();
    }
}

这段代码实际上并没有测试任何东西——它是一个冒烟测试,如果有的话——但它应该作为一个起点。另一个(可能)好的事情是,如果您还没有下载模型,它会为您下载模型。

于 2011-04-29T19:29:25.803 回答
10

URL http://bulba.sdsu.edu/jeanette/thesis/PennTags.html不再起作用。我在http://www.slideshare.net/gagan1667/opennlp-demo的第 14 张幻灯片上找到了以下内容

在此处输入图像描述

于 2015-04-07T07:20:49.077 回答
1

上面的答案确实提供了一种使用 OpenNLP 现有模型的方法,但是如果您需要训练自己的模型,也许以下内容可以提供帮助:

这是一个包含完整代码的详细教程:

https://dataturks.com/blog/opennlp-pos-tagger-training-java-example.php

根据您的域,您可以自动或手动构建数据集。手动构建这样的数据集真的很痛苦,像POS 标记器这样的工具可以帮助简化这个过程。

训练数据格式

训练数据作为文本文件传递,其中每一行是一个数据项。行中的每个单词都应以“word_LABEL”之类的格式标记,单词和标签名称之间用下划线“_”分隔。

anki_Brand overdrive_Brand
just_ModelName dance_ModelName 2018_ModelName
aoc_Brand 27"_ScreenSize monitor_Category
horizon_ModelName zero_ModelName dawn_ModelName
cm_Unknown 700_Unknown modem_Category
computer_Category

训练模型

这里重要的类是 POSModel,它保存了实际的模型。我们使用 POSTaggerME 类进行模型构建。下面是从训练数据文件构建模型的代码

public POSModel train(String filepath) {
  POSModel model = null;
  TrainingParameters parameters = TrainingParameters.defaultParams();
  parameters.put(TrainingParameters.ITERATIONS_PARAM, "100");

  try {
    try (InputStream dataIn = new FileInputStream(filepath)) {
        ObjectStream<String> lineStream = new PlainTextByLineStream(new InputStreamFactory() {
            @Override
            public InputStream createInputStream() throws IOException {
                return dataIn;
            }
        }, StandardCharsets.UTF_8);
        ObjectStream<POSSample> sampleStream = new WordTagSampleStream(lineStream);

        model = POSTaggerME.train("en", sampleStream, parameters, new POSTaggerFactory());
        return model;
    }
  }
  catch (Exception e) {
    e.printStackTrace();
  }
  return null;

}

使用模型进行标记。

最后,我们可以看到如何使用模型来标记未见过的查询:

    public void doTagging(POSModel model, String input) {
    input = input.trim();
    POSTaggerME tagger = new POSTaggerME(model);
    Sequence[] sequences = tagger.topKSequences(input.split(" "));
    for (Sequence s : sequences) {
        List<String> tags = s.getOutcomes();
        System.out.println(Arrays.asList(input.split(" ")) +" =>" + tags);
    }
}
于 2018-03-23T06:40:10.973 回答