/// <exception cref="System.IO.IOException"/>
public NERClassifierCombiner(bool applyNumericClassifiers, NERClassifierCombiner.Language nerLanguage, bool useSUTime, bool augmentRegexNER, Properties nscProps, params string[] loadPaths)
: base(nscProps, ClassifierCombiner.ExtractCombinationModeSafe(nscProps), loadPaths)
{
// NOTE: nscProps may contains sutime props which will not be recognized by the SeqClassifierFlags
this.applyNumericClassifiers = applyNumericClassifiers;
this.nerLanguage = nerLanguage;
this.useSUTime = useSUTime;
// check for which language to use for number sequence classifier
if (nerLanguage == NERClassifierCombiner.Language.Chinese)
{
this.nsc = new ChineseNumberSequenceClassifier(new Properties(), useSUTime, nscProps);
}
else
{
this.nsc = new NumberSequenceClassifier(new Properties(), useSUTime, nscProps);
}
if (augmentRegexNER)
{
this.gazetteMapping = ReadRegexnerGazette(DefaultPaths.DefaultNerGazetteMapping);
}
else
{
this.gazetteMapping = Java.Util.Collections.EmptyMap();
}
}
/// <summary>
/// This factory method is used to create the NERClassifierCombiner used in NERCombinerAnnotator
/// (and, thence, in StanfordCoreNLP).
/// </summary>
/// <param name="name">
/// A "x.y" format property name prefix (the "x" part). This is commonly null,
/// and then "ner" is used. If it is the empty string, then no property prefix is used.
/// </param>
/// <param name="passDownProperties">
/// Property names for which the property should be passed down
/// to the NERClassifierCombiner. The default is not to pass down, but pass down is
/// useful for things like charset encoding.
/// </param>
/// <param name="properties">
/// Various properties, including a list in "ner.model".
/// The used ones start with name + "." or are in passDownProperties
/// </param>
/// <returns>An NERClassifierCombiner with the given properties</returns>
public static NERClassifierCombiner CreateNERClassifierCombiner(string name, ICollection <string> passDownProperties, Properties properties)
{
string prefix = (name == null) ? "ner." : name.IsEmpty() ? string.Empty : name + '.';
string modelNames = properties.GetProperty(prefix + "model");
if (modelNames == null)
{
modelNames = DefaultPaths.DefaultNerThreeclassModel + ',' + DefaultPaths.DefaultNerMucModel + ',' + DefaultPaths.DefaultNerConllModel;
}
// but modelNames can still be empty string is set explicitly to be empty!
string[] models;
if (!modelNames.IsEmpty())
{
models = modelNames.Split(",");
}
else
{
// Allow for no real NER model - can just use numeric classifiers or SUTime
log.Info("WARNING: no NER models specified");
models = StringUtils.EmptyStringArray;
}
NERClassifierCombiner nerCombiner;
try
{
bool applyNumericClassifiers = PropertiesUtils.GetBool(properties, prefix + ApplyNumericClassifiersPropertyBase, ApplyNumericClassifiersDefault);
bool useSUTime = PropertiesUtils.GetBool(properties, prefix + NumberSequenceClassifier.UseSutimePropertyBase, NumberSequenceClassifier.UseSutimeDefault);
bool applyRegexner = PropertiesUtils.GetBool(properties, NERClassifierCombiner.ApplyGazetteProperty, NERClassifierCombiner.ApplyGazetteDefault);
Properties combinerProperties;
if (passDownProperties != null)
{
combinerProperties = PropertiesUtils.ExtractSelectedProperties(properties, passDownProperties);
if (useSUTime)
{
// Make sure SUTime parameters are included
Properties sutimeProps = PropertiesUtils.ExtractPrefixedProperties(properties, NumberSequenceClassifier.SutimeProperty + ".", true);
PropertiesUtils.OverWriteProperties(combinerProperties, sutimeProps);
}
}
else
{
// if passDownProperties is null, just pass everything through
combinerProperties = properties;
}
//Properties combinerProperties = PropertiesUtils.extractSelectedProperties(properties, passDownProperties);
NERClassifierCombiner.Language nerLanguage = NERClassifierCombiner.Language.FromString(properties.GetProperty(prefix + "language"), NERClassifierCombiner.Language.English);
nerCombiner = new NERClassifierCombiner(applyNumericClassifiers, nerLanguage, useSUTime, applyRegexner, combinerProperties, models);
}
catch (IOException e)
{
throw new RuntimeIOException(e);
}
return(nerCombiner);
}
public static NERClassifierCombiner.Language FromString(string name, NERClassifierCombiner.Language defaultValue)
{
if (name != null)
{
foreach (NERClassifierCombiner.Language l in NERClassifierCombiner.Language.Values())
{
if (Sharpen.Runtime.EqualsIgnoreCase(name, l.languageName))
{
return(l);
}
}
}
return(defaultValue);
}
public NERClassifierCombiner(bool applyNumericClassifiers, bool useSUTime, bool augmentRegexNER, params AbstractSequenceClassifier <CoreLabel>[] classifiers)
: base(classifiers)
{
this.applyNumericClassifiers = applyNumericClassifiers;
this.nerLanguage = NerLanguageDefault;
this.useSUTime = useSUTime;
this.nsc = new NumberSequenceClassifier(useSUTime);
if (augmentRegexNER)
{
this.gazetteMapping = ReadRegexnerGazette(DefaultPaths.DefaultNerGazetteMapping);
}
else
{
this.gazetteMapping = Java.Util.Collections.EmptyMap();
}
}
/// <exception cref="System.IO.IOException"/>
public NERClassifierCombiner(Properties props)
: base(props)
{
// todo [cdm 2015]: Could avoid constructing this if applyNumericClassifiers is false
applyNumericClassifiers = PropertiesUtils.GetBool(props, ApplyNumericClassifiersProperty, ApplyNumericClassifiersDefault);
nerLanguage = NERClassifierCombiner.Language.FromString(PropertiesUtils.GetString(props, NerLanguageProperty, null), NerLanguageDefault);
useSUTime = PropertiesUtils.GetBool(props, NumberSequenceClassifier.UseSutimeProperty, NumberSequenceClassifier.UseSutimeDefault);
nsc = new NumberSequenceClassifier(new Properties(), useSUTime, props);
if (PropertiesUtils.GetBool(props, NERClassifierCombiner.ApplyGazetteProperty, NERClassifierCombiner.ApplyGazetteDefault))
{
this.gazetteMapping = ReadRegexnerGazette(DefaultPaths.DefaultNerGazetteMapping);
}
else
{
this.gazetteMapping = Java.Util.Collections.EmptyMap();
}
}
/// <exception cref="System.IO.IOException"/>
/// <exception cref="System.InvalidCastException"/>
/// <exception cref="System.TypeLoadException"/>
public NERClassifierCombiner(ObjectInputStream ois, Properties props)
: base(ois, props)
{
// constructor which builds an NERClassifierCombiner from an ObjectInputStream
// read the useSUTime from disk
bool diskUseSUTime = ois.ReadBoolean();
if (props.GetProperty("ner.useSUTime") != null)
{
this.useSUTime = bool.Parse(props.GetProperty("ner.useSUTime"));
}
else
{
this.useSUTime = diskUseSUTime;
}
// read the applyNumericClassifiers from disk
bool diskApplyNumericClassifiers = ois.ReadBoolean();
if (props.GetProperty("ner.applyNumericClassifiers") != null)
{
this.applyNumericClassifiers = bool.Parse(props.GetProperty("ner.applyNumericClassifiers"));
}
else
{
this.applyNumericClassifiers = diskApplyNumericClassifiers;
}
this.nerLanguage = NerLanguageDefault;
// build the nsc, note that initProps should be set by ClassifierCombiner
this.nsc = new NumberSequenceClassifier(new Properties(), useSUTime, props);
if (PropertiesUtils.GetBool(props, NERClassifierCombiner.ApplyGazetteProperty, NERClassifierCombiner.ApplyGazetteDefault))
{
this.gazetteMapping = ReadRegexnerGazette(DefaultPaths.DefaultNerGazetteMapping);
}
else
{
this.gazetteMapping = Java.Util.Collections.EmptyMap();
}
}
