Example usage for opennlp.tools.postag POSTaggerME POSTaggerME

Introduction

In this page you can find the example usage for opennlp.tools.postag POSTaggerME POSTaggerME.

Prototype

public POSTaggerME(POSModel model) 

Source Link

Document

Initializes the current instance with the provided model.

Usage

From source file:org.sglover.nlp.CoreNLPEntityTagger.java

@Override
protected Entities getEntitiesImpl(String content) {
    Entities namedEntities = Entities.empty();

    SentenceModel sentenceModel = sentenceModels.get("en");
    SentenceDetector sentenceDetector = new SentenceDetectorME(sentenceModel);
    String[] sentences = sentenceDetector.sentDetect(content);

    TokenizerModel tm = tokenizerModels.get("en");
    TokenizerME wordBreaker = new TokenizerME(tm);

    for (String sentence : sentences) {
        String[] tokens = wordBreaker.tokenize(sentence);

        List<TextAnnotation> allTextAnnotations = new LinkedList<TextAnnotation>();

        POSModel posModel = posModels.get("en");
        POSTaggerME posme = new POSTaggerME(posModel);
        String[] posTags = posme.tag(tokens);

        List<String> npTokens = new LinkedList<>();

        ChunkerModel chunkerModel = chunkerModels.get("en");
        ChunkerME chunkerME = new ChunkerME(chunkerModel);
        Span[] chunks = chunkerME.chunkAsSpans(tokens, posTags);
        String[] chunkStrings = Span.spansToStrings(chunks, tokens);
        for (int i = 0; i < chunks.length; i++) {
            String chunkString = chunkStrings[i];
            logger.info("Chunk = " + chunkString + ", type = " + chunks[i].getType());
            if (chunks[i].getType().equals("NP")) {
                npTokens.add(chunkString);
            }/*ww  w  . j  a v a  2s  .  c  o  m*/
        }

        // findEntities(namedEntities, allTextAnnotations,
        // npTokens.toArray(new String[0]));
        findEntities(namedEntities, allTextAnnotations, tokens);
    }

    return namedEntities;
}

---

From source file:org.apache.stanbol.commons.opennlp.OpenNLP.java

/**
 * Getter for the "part-of-speech" tagger for the parsed language.
 * @param language the language//w  ww . j  av  a  2s. c  o m
 * @return the model or <code>null</code> if no model data are found
 * @throws InvalidFormatException in case the found model data are in the wrong format
 * @throws IOException on any error while reading the model data
 */
public POSTagger getPartOfSpeechTagger(String language) throws IOException {
    POSModel posModel = getPartOfSpeechModel(language);
    if (posModel != null) {
        return new POSTaggerME(posModel);
    } else {
        log.debug("No POS Model for language '{}'", language);
        return null;
    }
}

---

From source file:org.dbpedia.spotlight.spot.OpenNLPNGramSpotter.java

/**Extracts noun-phrase n-grams from the given piece of input text. 
 * @param text  A Text object containing the input from where to extract NP n-grams
 * @return A list of SurfaceFormOccurrence objects.
 *///from  w w  w.  jav  a 2 s. c o m
protected List<SurfaceFormOccurrence> extractNPNGrams(Text text) {
    String intext = text.text();
    //System.out.println("\n\nRR- nextractNPNGrams(...) method called! with text: " + intext + "\n\n");
    List<SurfaceFormOccurrence> npNgramSFLst = new ArrayList<SurfaceFormOccurrence>();
    SentenceDetectorME sentenceDetector = new SentenceDetectorME((SentenceModel) sentenceModel);
    TokenizerME tokenizer = new TokenizerME((TokenizerModel) tokenModel);
    POSTaggerME posTagger = new POSTaggerME((POSModel) posModel);
    ChunkerME chunker = new ChunkerME((ChunkerModel) chunkModel);

    Span[] sentSpans = sentenceDetector.sentPosDetect(intext);
    for (Span sentSpan : sentSpans) {
        String sentence = sentSpan.getCoveredText(intext).toString();
        int start = sentSpan.getStart();
        Span[] tokSpans = tokenizer.tokenizePos(sentence);
        String[] tokens = new String[tokSpans.length];
        // System.out.println("\n\nTokens:");
        for (int i = 0; i < tokens.length; i++) {
            tokens[i] = tokSpans[i].getCoveredText(sentence).toString();
            // System.out.println(tokens[i]);
        }
        String[] tags = posTagger.tag(tokens);
        Span[] chunks = chunker.chunkAsSpans(tokens, tags);
        for (Span chunk : chunks) {
            if ("NP".equals(chunk.getType())) {
                //Note: getStart()/getEnd() methods of Chunk spans only give the start and end token indexes of the chunk.
                //The actual Start/End positions of the chunk in the sentence need to be extracted from POS sentenceSpans.
                //They are offsets from the begining of the sentence in question. Need to add the start postion of the sentence
                //to compute the actual start/end offsets from the begining of the input text.
                int begin = tokSpans[chunk.getStart()].getStart();
                int end = tokSpans[chunk.getEnd() - 1].getEnd();
                List<Map<String, Integer>> ngrampos = extractNGramPos(chunk.getStart(), chunk.getEnd() + -1);
                extractNGrams(ngrampos, start, text, tokSpans, npNgramSFLst);
            }
        }
    }
    return npNgramSFLst;
}

---

From source file:os.Controller.java

public static String POSTag(String a) 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);

    ObjectStream<String> lineStream = new PlainTextByLineStream(new StringReader(a));

    perfMon.start();/*from   w  ww. j  av a2 s .c o  m*/
    String line, result = "";
    while ((line = lineStream.read()) != null) {

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

        POSSample sample = new POSSample(whitespaceTokenizerLine, tags);
        result = result + sample.toString();

        perfMon.incrementCounter();
    }
    perfMon.stopAndPrintFinalResult();
    textList.add(result);
    return result;
}

---

From source file:sentimental_analysis.pre.processor.WordBag.Tokenizer.PartsofSpeechFilter.java

private void getPOSTaggerME(POSModel Pmodel) {
    if (Pmodel == null) {
        System.out.println("POS Model is NULL!");
    }/*from  w  w w . ja  va  2  s  . c o  m*/
    try {
        POSTagger = new POSTaggerME(Pmodel);
    } catch (Exception ex) {
        System.out.println("Exception Thrown POSTaggerME (getPOSTaggerME) : " + ex.getMessage());
        System.out.println("Stack Trace");
        ex.printStackTrace();
    }
}

---

• «
• 1
• 2
• »