StanfordNLP for JAVA demo

依照 印度小哥的 视频 跑了一个小 demo

step 1 用 IDEA 构建一个 maven 项目，引入 相关依赖包，当前依赖包最新版本为 3.9.2

<dependency>
            <groupId>edu.stanford.nlp</groupId>
            <artifactId>stanford-corenlp</artifactId>
            <version>3.9.2</version>
        </dependency>
        <dependency>
            <groupId>edu.stanford.nlp</groupId>
            <artifactId>stanford-corenlp</artifactId>
            <version>3.9.2</version>
            <classifier>models</classifier>
        </dependency>

        <!--添加中文支持-->

        <dependency>
            <groupId>edu.stanford.nlp</groupId>
            <artifactId>stanford-corenlp</artifactId>
            <version>3.9.2</version>
            <classifier>models-chinese</classifier>
        </dependency>

step 2 使用 nlp 包

package com.ghc.corhort.query.utils;

import edu.stanford.nlp.coref.CorefCoreAnnotations;
import edu.stanford.nlp.coref.data.CorefChain;
import edu.stanford.nlp.ling.CoreAnnotations;
import edu.stanford.nlp.ling.CoreLabel;
import edu.stanford.nlp.pipeline.*;
import edu.stanford.nlp.semgraph.SemanticGraph;
import edu.stanford.nlp.semgraph.SemanticGraphCoreAnnotations;
import edu.stanford.nlp.trees.Tree;
import edu.stanford.nlp.trees.TreeCoreAnnotations;
import edu.stanford.nlp.util.CoreMap;

import java.util.*;

/**
 * @author ：Frank Li
 * @date ：Created in 2019/8/7 13:39
 * @description：${description}
 * @modified By：
 * @version: $version$
 */
public class Demo {
    public static void main(String[] args) {
        // creates a StanfordCoreNLP object, with POS tagging, lemmatization, NER, parsing, and coreference resolution
        Properties props = new Properties();
        props.setProperty("annotators", "tokenize, ssplit, pos, lemma, ner, parse, dcoref");
        StanfordCoreNLP pipeline = new StanfordCoreNLP(props);

        // read some text in the text variable
        String text = "I like eat apple!";

        // create an empty Annotation just with the given text
        Annotation document = new Annotation(text);

        // run all Annotators on this text
        pipeline.annotate(document);



        // these are all the sentences in this document
// a CoreMap is essentially a Map that uses class objects as keys and has values with custom types
        List<CoreMap> sentences = document.get(CoreAnnotations.SentencesAnnotation.class);

        for(CoreMap sentence: sentences) {
            // traversing the words in the current sentence
            // a CoreLabel is a CoreMap with additional token-specific methods
            for (CoreLabel token: sentence.get(CoreAnnotations.TokensAnnotation.class)) {
                // this is the text of the token
                String word = token.get(CoreAnnotations.TextAnnotation.class);
                // this is the POS tag of the token
                String pos = token.get(CoreAnnotations.PartOfSpeechAnnotation.class);
                // this is the NER label of the token
                String ne = token.get(CoreAnnotations.NamedEntityTagAnnotation.class);

                System.out.println("word:"+word+"-->pos:"+pos+"-->ne:"+ne);
            }

            // this is the parse tree of the current sentence
            Tree tree = sentence.get(TreeCoreAnnotations.TreeAnnotation.class);

            System.out.println(String.format("tree:\n%s",tree.toString()));
            // this is the Stanford dependency graph of the current sentence
            SemanticGraph dependencies = sentence.get(SemanticGraphCoreAnnotations.CollapsedCCProcessedDependenciesAnnotation.class);
        }

// This is the coreference link graph
// Each chain stores a set of mentions that link to each other,
// along with a method for getting the most representative mention
// Both sentence and token offsets start at 1!
        Map<Integer, CorefChain> graph =
                document.get(CorefCoreAnnotations.CorefChainAnnotation.class);
    }
}

输出结果

浅度原理

接下来要做 nlp2sql 的事情了

标签：nlp,JAVA,stanford,demo,token,StanfordNLP,edu,import,class
来源： https://www.cnblogs.com/Frank99/p/11325835.html