Java CoreMap类代码示例

import edu.stanford.nlp.util.CoreMap; //导入依赖的package包/类
/**
 * Split a document into array of sentences
 * 
 * @param text
 * @return
 * @throws Exception
 */
public static String[] extractSentences(String text) throws Exception {
	Properties props = new Properties();
	props.put("annotators", "tokenize, ssplit");
	StanfordCoreNLP pipeline = new StanfordCoreNLP();

	Annotation document = new Annotation(text);
	pipeline.annotate(document);

	List<CoreMap> sentences = document.get(SentencesAnnotation.class);
	String[] sentenceList = new String[sentences.size()];

	for (int i = 0; i < sentenceList.length; i++) {
		CoreMap sentence = sentences.get(i);
		sentenceList[i] = sentence.toString();
	}

	return sentenceList;
}
 

import edu.stanford.nlp.util.CoreMap; //导入依赖的package包/类
public int getStanfordSentimentRate(String sentimentText) {
    Properties props = new Properties();
    props.setProperty("annotators", "tokenize, ssplit, parse, sentiment");
    StanfordCoreNLP pipeline = new StanfordCoreNLP(props);
    //StanfordCoreNLP
    int totalRate = 0;
    String[] linesArr = sentimentText.split("\\.");
    for (int i = 0; i < linesArr.length; i++) {
        if (linesArr[i] != null) {
            Annotation annotation = pipeline.process(linesArr[i]);
            for (CoreMap sentence : annotation.get(CoreAnnotations.SentencesAnnotation.class)) {
                Tree tree = sentence.get(SentimentCoreAnnotations.SentimentAnnotatedTree.class);
                int score = RNNCoreAnnotations.getPredictedClass(tree);
                totalRate = totalRate + (score - 2);
            }
        }
    }
    return totalRate;
}
 

import edu.stanford.nlp.util.CoreMap; //导入依赖的package包/类
public LinkedList<String> tokenize(String text) {
    LinkedList<String> res = new LinkedList<>();
    if (text != null) {
        Annotation qaTokens = new Annotation(text);
        pipelineTokens.annotate(qaTokens);
        List<CoreMap> qssTokens = qaTokens.get(CoreAnnotations.SentencesAnnotation.class);
        for (CoreMap sentenceTokens : qssTokens) {
            ArrayList<CoreLabel> tokens = (ArrayList<CoreLabel>) sentenceTokens.get(CoreAnnotations.TokensAnnotation.class);
            for (CoreLabel t : tokens) {
                String lemma = t.lemma();
                String pos = t.tag();
                if (!stopwords.contains(lemma)) {
                    String rep = representativeProvider.getRepresentative(lemma, pos);
                    if (!stopwords.contains(rep)) {
                        res.add(rep);
                    }
                }
            }
        }
    }
    return res;
}
 

import edu.stanford.nlp.util.CoreMap; //导入依赖的package包/类
protected void annotate(StanfordCoreNLP pipeline, Annotation ann) {
	if (ann.get(CoreAnnotations.SentencesAnnotation.class) == null) {
		pipeline.annotate(ann);
	}
	else {
		if (ann.get(CoreAnnotations.SentencesAnnotation.class).size() == 1) {
			CoreMap sentence = ann.get(CoreAnnotations.SentencesAnnotation.class).get(0);

			for (CoreLabel token : sentence.get(CoreAnnotations.TokensAnnotation.class)) {
				token.remove(NaturalLogicAnnotations.OperatorAnnotation.class);
				token.remove(NaturalLogicAnnotations.PolarityAnnotation.class);
			}

			sentence.remove(NaturalLogicAnnotations.RelationTriplesAnnotation.class);
			sentence.remove(NaturalLogicAnnotations.EntailedSentencesAnnotation.class);
			sentence.remove(SemanticGraphCoreAnnotations.BasicDependenciesAnnotation.class);
			sentence.remove(SemanticGraphCoreAnnotations.EnhancedDependenciesAnnotation.class);
			sentence.remove(SemanticGraphCoreAnnotations.EnhancedPlusPlusDependenciesAnnotation.class);

			pipeline.annotate(ann);
		}
	}
}
 

import edu.stanford.nlp.util.CoreMap; //导入依赖的package包/类
public static void minimizeSubject(AnnotatedPhrase subject, SemanticGraph sg, ObjectOpenHashSet<String> collocations){
    // Do the safe minimization first
    SubjSafeMinimization.minimizeSubject(subject, sg);
    
    // If the subject is frequent, don't minimize anything
    if (collocations.contains(CoreNLPUtils.listOfWordsToLemmaString(subject.getWordList()).toLowerCase())){
        return;
    }
    
    // Minimization object
    Minimization simp = new Minimization(subject, sg, collocations);
    
    // remWords: list of words to be removed (reusable variable)
    // matchWords: list of matched words from the regex (reusable variable)
    List<CoreMap> remWords = new ArrayList<>();
    List<CoreMap> matchWords = new ArrayList<>(); 
    
    // Safe minimization on the noun phrases and named entities within the subj. phrase
    simp.nounPhraseDictMinimization(remWords, matchWords);
    simp.removeVerbsBeforeNouns(remWords, matchWords);
    simp.namedEntityDictionaryMinimization(remWords, matchWords);
}
 

import edu.stanford.nlp.util.CoreMap; //导入依赖的package包/类
/**
 * Minimize only the relations that are considered to have "non-frequent patterns"
 * @param rel: the relation phrase
 * @param sg: semantic graph of the sentence
 * @param freqRels: dictionary of multi-word expressions (frequent relations)
 */
public static void minimizeRelation(AnnotatedPhrase rel, SemanticGraph sg, ObjectOpenHashSet<String> collocations){
    // Do the safe minimization first
    RelSafeMinimization.minimizeRelation(rel, sg);
    
    // If the subject is frequent, don't minimize anything
    if (collocations.contains(CoreNLPUtils.listOfWordsToLemmaString(rel.getWordList()).toLowerCase())){
        return;
    }
    
    // Do the safe minimization first
    RelSafeMinimization.minimizeRelation(rel, sg);
    
    // remWords: list of words to be removed (reusable variable)
    // matchWords: list of matched words from the regex (reusable variable)
    List<CoreMap> remWords = new ArrayList<>();
    List<CoreMap> matchWords = new ArrayList<>(); 
    
    // Move to the dict. minimization of the noun phrases within the relation
    Minimization simp = new Minimization(rel, sg, collocations);
    simp.nounPhraseDictMinimization(remWords, matchWords);
    simp.namedEntityDictionaryMinimization(remWords, matchWords);
}
 

import edu.stanford.nlp.util.CoreMap; //导入依赖的package包/类
/**
 * Given a list of words to be removed and a list of matched nodes, remove the words to be removed from the phrase and
 * empty that list, also empty the list of matched nodes
 * @param remWords
 * @param matchedNodes
 */
public void dropWords(List<CoreMap> remWords, List<CoreMap> matchWords){
    matchWords.clear();
    // in addition to removing the words, save them in a separate list
    ObjectArrayList<SemanticGraphEdge> droppedEdges = CoreNLPUtils.listOfCoreMapWordsToParentEdges(this.sg, remWords);
    /*ObjectArrayList<SemanticGraphEdge> droppedEdges = new ObjectArrayList<SemanticGraphEdge>();
    for (IndexedWord word: remWordsArray) {
        SemanticGraphEdge edge = this.sg.getEdge(this.sg.getParent(word), word);
        droppedEdges.add(edge);
    }*/
    this.phrase.addDroppedEdges(droppedEdges);
    this.phrase.addDroppedWords(CoreNLPUtils.getWordListFromCoreMapList(remWords));
    // remove words
    this.phrase.removeCoreLabelWordsFromList(remWords);
    remWords.clear();
}
 

import edu.stanford.nlp.util.CoreMap; //导入依赖的package包/类
/** Given a phrase, if it contains NERs, make a dictionary minimization around them **/
public void namedEntityDictionaryMinimization(List<CoreMap> remWords, List<CoreMap> matchWords){
    // If (.* DT+ [RB|JJ]* NER+ .*) => drop (DT+)
    this.tPattern = TokenSequencePattern.compile(REGEX.T_RB_JJ_NER);
    this.tMatcher = tPattern.getMatcher(this.phrase.getWordCoreLabelList());
    while (this.tMatcher.find()){         
        matchWords = tMatcher.groupNodes();
        
        for (CoreMap cm: matchWords){
            CoreLabel cl = new CoreLabel(cm);
            if (cl.lemma() == null) cl.setLemma(cl.word());
            
            // Check if the word is DT, drop it
            if ((CoreNLPUtils.isAdj(cl.tag()) || CoreNLPUtils.isAdverb(cl.tag())) 
                    && cl.ner().equals(NE_TYPE.NO_NER)){
                remWords.add(cm);   
            }
        }
        
        // Drop the words not found in dict. 
        this.dropWordsNotFoundInDict(matchWords, remWords);
    }
    
    // Do the safe minimization
    this.namedEntitySafeMinimization(remWords, matchWords);
}
 

import edu.stanford.nlp.util.CoreMap; //导入依赖的package包/类
/**
 * Minimize only the objects that are considered to have "non-frequent patterns"
 * @param obj: the object phrase
 * @param sg: semantic graph of the sentence
 * @param freqObjs: dictionary of multi-word expressions (frequent objects)
 */
public static void minimizeObject(AnnotatedPhrase obj, SemanticGraph sg, ObjectOpenHashSet<String> collocations){
    // Do the safe minimization first
    ObjSafeMinimization.minimizeObject(obj, sg);
    
    // If the object is frequent, don't minimize anything
    if (collocations.contains(CoreNLPUtils.listOfWordsToLemmaString(obj.getWordList()).toLowerCase())){
        return;
    }
    
    // Minimization object
    Minimization simp = new Minimization(obj, sg, collocations);
    
    // remWords: list of words to be removed (reusable variable)
    // matchWords: list of matched words from the regex (reusable variable)
    List<CoreMap> remWords = new ArrayList<>();
    List<CoreMap> matchWords = new ArrayList<>(); 
    
    // Safe minimization on the noun phrases and named entities within the subj. phrase
    simp.nounPhraseDictMinimization(remWords, matchWords);
    simp.namedEntityDictionaryMinimization(remWords, matchWords);
}
 

import edu.stanford.nlp.util.CoreMap; //导入依赖的package包/类
public List<List<String>> lemmatize(String documentText)
{
	List<List<String>> lemmas = new ArrayList<List<String>>();

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

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

	// Iterate over all of the sentences found
	List<CoreMap> sentences = document.get(SentencesAnnotation.class);
	for(CoreMap sentence: sentences) {
		// Iterate over all tokens in a sentence
		List<String> sentence_lemmas = new ArrayList<String>();
		for (CoreLabel token: sentence.get(TokensAnnotation.class)) {
			// Retrieve and add the lemma for each word into the
			// list of lemmas
			sentence_lemmas.add(token.get(LemmaAnnotation.class));
		}
		lemmas.add(sentence_lemmas);
	}

	return lemmas;
}
 

import edu.stanford.nlp.util.CoreMap; //导入依赖的package包/类
public Pair<List<String>, List<String>> tagAndTokenize(String documentText)
{
	List<String> tags = new ArrayList<String>();
	List<String> tokens = new ArrayList<String>();

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

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

	// Iterate over all of the sentences found
	List<CoreMap> sentences = document.get(SentencesAnnotation.class);
	for(CoreMap sentence: sentences) {
		// Iterate over all tokens in a sentence
		for (CoreLabel token: sentence.get(TokensAnnotation.class)) {
			// Retrieve and add the lemma for each word into the
			// list of lemmas
			tags.add(token.get(PartOfSpeechAnnotation.class));
			tokens.add(token.word());
		}
	}

	return new Pair<List<String>, List<String>>(tags, tokens);
}
 

import edu.stanford.nlp.util.CoreMap; //导入依赖的package包/类
public List<String> tag(String documentText)
{
	List<String> tags = new ArrayList<String>();

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

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

	// Iterate over all of the sentences found
	List<CoreMap> sentences = document.get(SentencesAnnotation.class);
	for(CoreMap sentence: sentences) {
		// Iterate over all tokens in a sentence
		for (CoreLabel token: sentence.get(TokensAnnotation.class)) {
			// Retrieve and add the lemma for each word into the
			// list of lemmas
			tags.add(token.get(PartOfSpeechAnnotation.class));
		}
	}

	return tags;
}
 

import edu.stanford.nlp.util.CoreMap; //导入依赖的package包/类
/**
 * Prepares the check for a temporal expression.
 * 
 * @param cell
 *            Holds the column´s cell
 * @param pipeline
 *            Used for temporal expressions.
 * @param result
 *            Holds the intermediate result before executing this operation.
 * @return Holds the intermediate result after executing this operation.
 */

private int prepareSUTParser(String cell, AnnotationPipeline pipeline,
		int result) {
	if ((!cell.trim().isEmpty()) && (!cell.trim().equals("-")
			&& !cell.trim().equals("--") && !cell.trim().equals("---")
			&& !cell.trim().equals("n/a") && !cell.trim().equals("N/A")
			&& !cell.trim().equals("(n/a)")
			&& !cell.trim().equals("Unknown")
			&& !cell.trim().equals("unknown") && !cell.trim().equals("?")
			&& !cell.trim().equals("??") && !cell.trim().equals(".")
			&& !cell.trim().equals("null") && !cell.trim().equals("NULL")
			&& !cell.trim().equals("Null"))) {
		Annotation annotation = new Annotation(cell);
		annotation.set(CoreAnnotations.DocDateAnnotation.class,
				"2013-07-14");
		pipeline.annotate(annotation);

		List<CoreMap> timexAnnsAll = annotation
				.get(TimeAnnotations.TimexAnnotations.class);
		if (timexAnnsAll != null)
			if (!timexAnnsAll.isEmpty())
				result++;
	}
	return result;
}
 

import edu.stanford.nlp.util.CoreMap; //导入依赖的package包/类
public static void main(String[] args) {

        // 载入自定义的Properties文件
        StanfordCoreNLP pipeline = new StanfordCoreNLP("CoreNLP-chinese.properties");

        // 用一些文本来初始化一个注释。文本是构造函数的参数。
        Annotation annotation;

        annotation = pipeline.process("我爱北京天安门");

        // 从注释中获取CoreMap List，并取第0个值
        List<CoreMap> sentences = annotation.get(CoreAnnotations.SentencesAnnotation.class);
        CoreMap sentence = sentences.get(0);

        // 从CoreMap中取出CoreLabel List，逐一打印出来
        List<CoreLabel> tokens = sentence.get(CoreAnnotations.TokensAnnotation.class);
        System.out.println("字/词");
        System.out.println("-----------------------------");
        for (CoreLabel token : tokens) {
            String word = token.getString(TextAnnotation.class);
//            String pos = token.getString(PartOfSpeechAnnotation.class);
//            String ner = token.getString(NamedEntityTagAnnotation.class);
            System.out.println(word);
        }

    }
 

import edu.stanford.nlp.util.CoreMap; //导入依赖的package包/类
public static int findSentiment(String tweet) {

		int mainSentiment = 0;
		if (tweet != null && tweet.length() > 0) {
			int longest = 0;
			Annotation annotation = pipeline.process(tweet);
			for (CoreMap sentence : annotation
					.get(CoreAnnotations.SentencesAnnotation.class)) {
				Tree tree = sentence
						.get(SentimentCoreAnnotations.SentimentAnnotatedTree.class);
				int sentiment = RNNCoreAnnotations.getPredictedClass(tree);
				String partText = sentence.toString();
				if (partText.length() > longest) {
					mainSentiment = sentiment;
					longest = partText.length();
				}

			}
		}
		return mainSentiment;
	}