edu.stanford.nlp.coref.statistical.FeatureExtractorRunner Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of stanford-corenlp Show documentation
Show all versions of stanford-corenlp Show documentation
Stanford CoreNLP provides a set of natural language analysis tools which can take raw English language text input and give the base forms of words, their parts of speech, whether they are names of companies, people, etc., normalize dates, times, and numeric quantities, mark up the structure of sentences in terms of phrases and word dependencies, and indicate which noun phrases refer to the same entities. It provides the foundational building blocks for higher level text understanding applications.
package edu.stanford.nlp.coref.statistical;
import java.util.ArrayList;
import java.util.List;
import java.util.Map;
import java.util.Properties;
import edu.stanford.nlp.coref.CorefDocumentProcessor;
import edu.stanford.nlp.coref.data.Dictionaries;
import edu.stanford.nlp.coref.data.Document;
import edu.stanford.nlp.io.IOUtils;
import edu.stanford.nlp.util.Pair;
/**
* Runs feature extraction over coreference documents.
* @author Kevin Clark
*/
public class FeatureExtractorRunner implements CorefDocumentProcessor {
private final FeatureExtractor extractor;
private final Compressor compressor;
private final Map, Boolean>> dataset;
private final List documents;
public FeatureExtractorRunner(Properties props, Dictionaries dictionaries) {
documents = new ArrayList<>();
compressor = new Compressor<>();
extractor = new FeatureExtractor(props, dictionaries, compressor);
try {
dataset = IOUtils.readObjectFromFile(StatisticalCorefTrainer.datasetFile);
} catch(Exception e) {
throw new RuntimeException("Error initializing FeatureExtractorRunner", e);
}
}
@Override
public void process(int id, Document document) {
if (dataset.containsKey(id)) {
documents.add(extractor.extract(id, document, dataset.get(id)));
}
}
@Override
public void finish() throws Exception {
IOUtils.writeObjectToFile(documents, StatisticalCorefTrainer.extractedFeaturesFile);
IOUtils.writeObjectToFile(compressor, StatisticalCorefTrainer.compressorFile);
}
}