Example usage for edu.stanford.nlp.pipeline WordsToSentencesAnnotator WordsToSentencesAnnotator

Introduction

In this page you can find the example usage for edu.stanford.nlp.pipeline WordsToSentencesAnnotator WordsToSentencesAnnotator.

Prototype

public WordsToSentencesAnnotator(boolean verbose, String boundaryTokenRegex, Set<String> boundaryToDiscard,
            Set<String> htmlElementsToDiscard, String newlineIsSentenceBreak, String boundaryMultiTokenRegex,
            Set<String> tokenRegexesToDiscard) 

Source Link

Usage

From source file:de.tudarmstadt.ukp.dkpro.core.corenlp.CoreNlpSegmenter.java

License:Open Source License

@Override
public void initialize(UimaContext aContext) throws ResourceInitializationException {
    super.initialize(aContext);

    tokenizerAnnotator = new ModelProviderBase<TokenizerAnnotator>(this, "corenlp", "tokenizer") {
        {//  w  w  w . ja  va2s .c  o  m
            setDefault(LOCATION, NOT_REQUIRED);
        }

        @Override
        protected TokenizerAnnotator produceResource(URL aUrl) throws IOException {
            Properties props = getAggregatedProperties();

            Properties coreNlpProps = new Properties();
            coreNlpProps.setProperty("tokenize.language", props.getProperty(LANGUAGE));
            //coreNlpProps.setProperty("tokenize.class", null);
            //coreNlpProps.setProperty("tokenize.whitespace", "false");
            //coreNlpProps.setProperty("tokenize.options", null);
            //coreNlpProps.setProperty("tokenize.keepeol", "false");

            String extraOptions = null;

            TokenizerAnnotator annotator = new TokenizerAnnotator(verbose, coreNlpProps, extraOptions);

            return annotator;
        }
    };

    sentenceAnnotator = new ModelProviderBase<WordsToSentencesAnnotator>(this, "corenlp", "sentence") {
        {
            setDefault(LOCATION, NOT_REQUIRED);
        }

        @Override
        protected WordsToSentencesAnnotator produceResource(URL aUrl) throws IOException {
            WordsToSentencesAnnotator annotator = new WordsToSentencesAnnotator(verbose, boundaryTokenRegex,
                    boundaryToDiscard, htmlElementsToDiscard, newlineIsSentenceBreak, boundaryMultiTokenRegex,
                    tokenRegexesToDiscard);

            return annotator;
        }
    };
}

---