最近工作需要，研究學習 NLP ，但是苦於官方文檔太過紛繁，容易找不到重點，於是打算自己寫一份學習線路

鏈接地址：https://pan.baidu.com/s/1myVT-yMzqzJIcl50mGs2JA
提取密碼：tw6r

參考文檔:

StanfordNLPAPI

依照印度小哥的視頻跑了一個小 demo

step 1 用 IDEA 構建一個 maven 項目，引入相關依賴包，當前依賴包最新版本為 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);
    }
}

輸出結果

淺度原理


stanford corenlp的TokensRegex
最近做一些音樂類、讀物類的自然語言理解，就調研使用了下Stanford corenlp，記錄下來。

功能
Stanford Corenlp是一套自然語言分析工具集包括：

POS(part of speech tagger)-標注詞性
NER(named entity recognizer)-實體名識別
Parser樹-分析句子的語法結構，如識別出短語詞組、主謂賓等
Coreference Resolution-指代消解，找出句子中代表同一個實體的詞。下文的I/my，Nader/he表示的是同一個人
　　





Sentiment Analysis-情感分析
Bootstrapped pattern learning-自展的模式學習（也不知道翻譯對不對，大概就是可以無監督的提取一些模式，如提取實體名）
Open IE(Information Extraction)-從純文本中提取有結構關系組，如"Barack Obama was born in Hawaii" =》 (Barack Obama; was born in; Hawaii)
需求
語音交互類的應用（如語音助手、智能音箱echo）收到的通常是口語化的自然語言，如：我想聽一個段子，給我來個牛郎織女的故事，要想精確的返回結果，就需要提出有用的主題詞，段子/牛郎織女/故事。看了一圈就想使用下corenlp的TokensRegex，基於tokens序列的正則表達式。因為它提供的可用的工具有：正則表達式、分詞、詞性、實體類別，另外還可以自己指定實體類別，如指定牛郎織女是READ類別的實體。