Multi-term named entities in Stanford Named Entity Recognizer

Question

I\'m using the Stanford Named Entity Recognizer http://nlp.stanford.edu/software/CRF-NER.shtml and it\'s working fine. This is

    List&         


        

Answer 1

Here is my full code, I use Stanford core NLP and write algorithm to concatenate Multi Term names.

import edu.stanford.nlp.ling.CoreAnnotations;
import edu.stanford.nlp.ling.CoreLabel;
import edu.stanford.nlp.pipeline.Annotation;
import edu.stanford.nlp.pipeline.StanfordCoreNLP;
import edu.stanford.nlp.util.CoreMap;
import org.apache.log4j.Logger;

import java.util.ArrayList;
import java.util.List;
import java.util.Properties;

/**
 * Created by Chanuka on 8/28/14 AD.
 */
public class FindNameEntityTypeExecutor {

private static Logger logger = Logger.getLogger(FindNameEntityTypeExecutor.class);

private StanfordCoreNLP pipeline;

public FindNameEntityTypeExecutor() {
    logger.info("Initializing Annotator pipeline ...");

    Properties props = new Properties();

    props.setProperty("annotators", "tokenize, ssplit, pos, lemma, ner");

    pipeline = new StanfordCoreNLP(props);

    logger.info("Annotator pipeline initialized");
}

List findNameEntityType(String text, String entity) {
    logger.info("Finding entity type matches in the " + text + " for entity type, " + entity);

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

    // run all Annotators on this text
    pipeline.annotate(document);
    List sentences = document.get(CoreAnnotations.SentencesAnnotation.class);
    List matches = new ArrayList();

    for (CoreMap sentence : sentences) {

        int previousCount = 0;
        int count = 0;
        // 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)) {
            String word = token.get(CoreAnnotations.TextAnnotation.class);

            int previousWordIndex;
            if (entity.equals(token.get(CoreAnnotations.NamedEntityTagAnnotation.class))) {
                count++;
                if (previousCount != 0 && (previousCount + 1) == count) {
                    previousWordIndex = matches.size() - 1;
                    String previousWord = matches.get(previousWordIndex);
                    matches.remove(previousWordIndex);
                    previousWord = previousWord.concat(" " + word);
                    matches.add(previousWordIndex, previousWord);

                } else {
                    matches.add(word);
                }
                previousCount = count;
            }
            else
            {
                count=0;
                previousCount=0;
            }


        }

    }
    return matches;
}
}