Examples of edu.stanford.nlp.ie.regexp.NumberSequenceClassifier

edu.stanford.nlp.ie.regexp.NumberSequenceClassifier
A set of deterministic rules for marking certain entities, to add categories and to correct for failures of statistical NER taggers. This is an extremely simple and ungeneralized implementation of AbstractSequenceClassifier that was written for PASCAL RTE. It could profitably be extended and generalized. It marks a NUMBER category based on part-of-speech tags in a deterministic manner. It marks an ORDINAL category based on word form in a deterministic manner. It tags as MONEY currency signs and things tagged CD after a currency sign. It marks a number before a month name as a DATE. It marks as a DATE a word of the form xx/xx/xxxx (where x is a digit from a suitable range). It marks as a TIME a word of the form x(x):xx (where x is a digit). It marks everything else tagged "CD" as a NUMBER, and instances of "and" appearing between CD tags in contexts suggestive of a number. It requires text to be POS-tagged (have the getString(TagAnnotation.class) attribute). Effectively these rules assume that this classifier will be used as a secondary classifier by code such as ClassifierCombiner: it will mark most CD as NUMBER, and it is assumed that something else with higher priority is marking ones that are PERCENT, ADDRESS, etc. @author Christopher Manning @author Mihai (integrated with NumberNormalizer, SUTime)

        }
      }
      copyL.add(new CoreLabel(l.get(i)));
    }
    // run NumberSequenceClassifier
    AbstractSequenceClassifier<CoreLabel> nsc = new NumberSequenceClassifier();
    copyL = nsc.classify(copyL);
    // update entity only if it was not O
    for (int i = 0; i < sz; i++) {
      E before = l.get(i);
      CoreLabel nscAnswer = copyL.get(i);
      if (before.get(CoreAnnotations.NamedEntityTagAnnotation.class) == null && before.get(CoreAnnotations.NamedEntityTagAnnotation.class).equals(BACKGROUND_SYMBOL) &&

View Full Code Here

    throws FileNotFoundException
  {
    super(props);
    applyNumericClassifiers = PropertiesUtils.getBool(props, APPLY_NUMERIC_CLASSIFIERS_PROPERTY, APPLY_NUMERIC_CLASSIFIERS_DEFAULT);
    useSUTime = PropertiesUtils.getBool(props, NumberSequenceClassifier.USE_SUTIME_PROPERTY, NumberSequenceClassifier.USE_SUTIME_DEFAULT);
    nsc = new NumberSequenceClassifier(new Properties(), useSUTime, props);
  }

View Full Code Here

    throws FileNotFoundException
  {
    super(loadPaths);
    this.applyNumericClassifiers = applyNumericClassifiers;
    this.useSUTime = useSUTime;
    this.nsc = new NumberSequenceClassifier(useSUTime);
  }

View Full Code Here

    throws FileNotFoundException
  {
    super(ClassifierCombiner.extractCombinationModeSafe(nscProps), loadPaths);
    this.applyNumericClassifiers = applyNumericClassifiers;
    this.useSUTime = useSUTime;
    this.nsc = new NumberSequenceClassifier(new Properties(), useSUTime, nscProps);
  }

View Full Code Here

    throws FileNotFoundException
  {
    super(classifiers);
    this.applyNumericClassifiers = applyNumericClassifiers;
    this.useSUTime = useSUTime;
    this.nsc = new NumberSequenceClassifier(useSUTime);
  }

View Full Code Here

  }


  public NumberAnnotator(String backgroundSymbol, boolean verbose, boolean useSUTime) {
    BACKGROUND_SYMBOL = backgroundSymbol;
    VERBOSE = verbose;
    nsc = new NumberSequenceClassifier(useSUTime);
  }

View Full Code Here

    BACKGROUND_SYMBOL = props.getProperty(property, DEFAULT_BACKGROUND_SYMBOL);
    boolean useSUTime = PropertiesUtils.getBool(props,
        NumberSequenceClassifier.USE_SUTIME_PROPERTY,
        NumberSequenceClassifier.USE_SUTIME_DEFAULT);
    VERBOSE = false;
    nsc = new NumberSequenceClassifier(useSUTime);
  }

View Full Code Here

TOP

Related Classes of edu.stanford.nlp.ie.regexp.NumberSequenceClassifier

edu.stanford.nlp.ie.NERClassifierCombiner

edu.stanford.nlp.ie.QuantifiableEntityNormalizer

edu.stanford.nlp.ling.CoreLabel

edu.stanford.nlp.pipeline.Annotation

edu.stanford.nlp.pipeline.NumberAnnotator

edu.stanford.nlp.time.Timex

edu.stanford.nlp.util.CoreMap

java.util.Properties

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.