protected AbstractParserEventStream(
IObjectStream <Parse> samples,
IHeadRules headRules,
ParserEventTypeEnum type,
Dictionary.Dictionary dictionary) : base(samples)
{
Rules = headRules;
Punctuation = headRules.PunctuationTags;
Dictionary = dictionary;
FixPossesives = false;
Type = type;
#pragma warning disable 618
switch (type)
{
case ParserEventTypeEnum.Chunk:
chunkerContextGenerator = new ChunkContextGenerator();
break;
case ParserEventTypeEnum.Tag:
posContextGenerator = new DefaultPOSContextGenerator(null);
break;
}
#pragma warning restore 618
}
/// <summary>
/// Initializes a new instance of the <see cref="ChunkerME"/> with the specified <see cref="ChunkerModel"/>.
/// </summary>
/// <param name="model">The chunker model.</param>
public ChunkerME(ChunkerModel model)
{
contextGenerator = model.Factory.GetContextGenerator();
sequenceValidator = model.Factory.GetSequenceValidator();
this.model = model.ChunkerSequenceModel ?? new BeamSearch(model.BeamSize, model.MaxentModel);
}
/// <summary>
/// Initializes the current instance with the specified model and the specified beam size.
/// </summary>
/// <param name="model">The model for this chunker</param>
/// <param name="beamSize">The size of the beam that should be used when decoding sequences.</param>
/// <param name="sequenceValidator">The <see cref="ISequenceValidator{String}"/> to determines whether the outcome is valid for the preceding sequence. This can be used to implement constraints on what sequences are valid..</param>
/// <param name="contextGenerator">The context generator.</param>
internal ChunkerME(ChunkerModel model, int beamSize, ISequenceValidator<string> sequenceValidator, IChunkerContextGenerator contextGenerator) {
// This method is marked as deprecated in the OpenNLP, but it is required in the Parser,
// I could change the cg in the factory, but its not ideal in this situation (i think) :P
this.sequenceValidator = sequenceValidator;
this.contextGenerator = contextGenerator;
this.model = model.ChunkerSequenceModel ?? new BeamSearch(beamSize, model.MaxentModel);
}
/// <summary>
/// Initializes the current instance with the specified model and the specified beam size.
/// </summary>
/// <param name="model">The model for this chunker</param>
/// <param name="beamSize">The size of the beam that should be used when decoding sequences.</param>
/// <param name="sequenceValidator">The <see cref="ISequenceValidator{String}"/> to determines whether the outcome is valid for the preceding sequence. This can be used to implement constraints on what sequences are valid..</param>
/// <param name="contextGenerator">The context generator.</param>
internal ChunkerME(ChunkerModel model, int beamSize, ISequenceValidator <string> sequenceValidator, IChunkerContextGenerator contextGenerator)
{
// This method is marked as deprecated in the OpenNLP, but it is required in the Parser,
// I could change the cg in the factory, but its not ideal in this situation (i think) :P
this.sequenceValidator = sequenceValidator;
this.contextGenerator = contextGenerator;
this.model = model.ChunkerSequenceModel ?? new BeamSearch(beamSize, model.MaxentModel);
}
/// <summary>
/// Initializes a new instance of the <see cref="ChunkSampleSequenceStream" /> class using the given parameters.
/// </summary>
/// <param name="samples">The chunk samples.</param>
/// <param name="contextGenerator">The chunker context generator.</param>
/// <exception cref="System.ArgumentNullException">
/// The <paramref name="samples"/> is null.
/// or
/// The <paramref name="contextGenerator"/> is null.
/// </exception>
public ChunkSampleSequenceStream(IObjectStream<ChunkSample> samples, IChunkerContextGenerator contextGenerator) {
if (samples == null)
throw new ArgumentNullException("samples");
if (contextGenerator == null)
throw new ArgumentNullException("contextGenerator");
this.samples = samples;
this.contextGenerator = contextGenerator;
}
/// <summary>
/// Creates a new event reader based on the specified data reader using the specified context generator.
/// </summary>
/// <param name="dataReader">
/// The data reader for this event reader.
/// </param>
/// <param name="contextGenerator">
/// The context generator which should be used in the creation of events for this event reader.
/// </param>
public ChunkerEventReader(SharpEntropy.ITrainingDataReader <string> dataReader, IChunkerContextGenerator contextGenerator)
{
mContextGenerator = contextGenerator;
mDataReader = dataReader;
mEventIndex = 0;
if (dataReader.HasNext())
{
AddNewEvents();
}
else
{
mEvents = new SharpEntropy.TrainingEvent[0];
}
}
/// <summary>
/// Creates a new event reader based on the specified data reader using the specified context generator.
/// </summary>
/// <param name="dataReader">
/// The data reader for this event reader.
/// </param>
/// <param name="contextGenerator">
/// The context generator which should be used in the creation of events for this event reader.
/// </param>
public ChunkerEventReader(SharpEntropy.ITrainingDataReader<string> dataReader, IChunkerContextGenerator contextGenerator)
{
mContextGenerator = contextGenerator;
mDataReader = dataReader;
mEventIndex = 0;
if (dataReader.HasNext())
{
AddNewEvents();
}
else
{
mEvents = new SharpEntropy.TrainingEvent[0];
}
}
/// <summary>
/// Initializes a new instance of the <see cref="ChunkSampleSequenceStream" /> class using the given parameters.
/// </summary>
/// <param name="samples">The chunk samples.</param>
/// <param name="contextGenerator">The chunker context generator.</param>
/// <exception cref="System.ArgumentNullException">
/// The <paramref name="samples"/> is null.
/// or
/// The <paramref name="contextGenerator"/> is null.
/// </exception>
public ChunkSampleSequenceStream(IObjectStream <ChunkSample> samples, IChunkerContextGenerator contextGenerator)
{
if (samples == null)
{
throw new ArgumentNullException(nameof(samples));
}
if (contextGenerator == null)
{
throw new ArgumentNullException(nameof(contextGenerator));
}
this.samples = samples;
this.contextGenerator = contextGenerator;
}
public ChunkBeamSearch(MaximumEntropyChunker maxentChunker, int size, IChunkerContextGenerator contextGenerator, SharpEntropy.IMaximumEntropyModel model) : base(size, contextGenerator, model)
{
mMaxentChunker = maxentChunker;
}
/// <summary>
/// Creates a chunker using the specified model and context generator and decodes the
/// model using a beam search of the specified size.
/// </summary>
/// <param name="model">The maximum entropy model for this chunker</param>
/// <param name="contextGenerator">The context generator to be used by the specified model</param>
/// <param name="beamSize">The size of the beam that should be used when decoding sequences</param>
public MaximumEntropyChunker(SharpEntropy.IMaximumEntropyModel model, IChunkerContextGenerator contextGenerator, int beamSize)
{
Beam = new ChunkBeamSearch(this, beamSize, contextGenerator, model);
Model = model;
}
/// <summary>
/// Creates a chunker using the specified model and context generator and decodes the
/// model using a beam search of the specified size.
/// </summary>
/// <param name="model">
/// The maximum entropy model for this chunker.
/// </param>
/// <param name="contextGenerator">
/// The context generator to be used by the specified model.
/// </param>
/// <param name="beamSize">
/// The size of the beam that should be used when decoding sequences.
/// </param>
public MaximumEntropyChunker(SharpEntropy.IMaximumEntropyModel model, IChunkerContextGenerator contextGenerator, int beamSize)
{
mBeam = new ChunkBeamSearch(this, beamSize, contextGenerator, model);
mModel = model;
}
public ChunkBeamSearch(MaximumEntropyChunker maxentChunker, int size, IChunkerContextGenerator contextGenerator, SharpEntropy.IMaximumEntropyModel model)
: base(size, contextGenerator, model)
{
_maxentChunker = maxentChunker;
}
/// <summary>
/// Creates a chunker using the specified model and context generator.
/// </summary>
/// <param name="model">The maximum entropy model for this chunker</param>
/// <param name="contextGenerator">The context generator to be used by the specified model</param>
public MaximumEntropyChunker(SharpEntropy.IMaximumEntropyModel model, IChunkerContextGenerator contextGenerator):
this(model, contextGenerator, 10){}
/// <summary>
/// Creates a chunker using the specified model and context generator.
/// </summary>
/// <param name="model">
/// The maximum entropy model for this chunker.
/// </param>
/// <param name="contextGenerator">
/// The context generator to be used by the specified model.
/// </param>
public MaximumEntropyChunker(MaxEntropyModel_Interface model, IChunkerContextGenerator contextGenerator):this(model, contextGenerator, 10)
{
}
/// <summary>
/// Initializes a new instance of the <see cref="ChunkerME"/> with the specified <see cref="ChunkerModel"/>.
/// </summary>
/// <param name="model">The chunker model.</param>
public ChunkerME(ChunkerModel model) {
contextGenerator = model.Factory.GetContextGenerator();
sequenceValidator = model.Factory.GetSequenceValidator();
this.model = model.ChunkerSequenceModel ?? new BeamSearch(model.BeamSize, model.MaxentModel);
}
public ChunkBeamSearch(MaximumEntropyChunker maxentChunker, int size, IChunkerContextGenerator contextGenerator, MaxEntropyModel_Interface model):base(size, contextGenerator, model)
{
mMaxentChunker = maxentChunker;
}
/// <summary>
/// Creates a chunker using the specified model and context generator.
/// </summary>
/// <param name="model">
/// The maximum entropy model for this chunker.
/// </param>
/// <param name="contextGenerator">
/// The context generator to be used by the specified model.
/// </param>
public MaximumEntropyChunker(SharpEntropy.IMaximumEntropyModel model, IChunkerContextGenerator contextGenerator) : this(model, contextGenerator, 10)
{
}
/// <summary>
/// Creates a new event stream based on the specified data stream using the specified context generator.
/// </summary>
/// <param name="samples">The samples for this event stream.</param>
/// <param name="cg">The context generator which should be used in the creation of events for this event stream.</param>
public ChunkerEventStream(IObjectStream <ChunkSample> samples, IChunkerContextGenerator cg) : base(samples)
{
this.cg = cg;
}
/// <summary>
/// Initializes a new instance of the <see cref="ChunkSampleSequenceStream"/> class using the given parameters.
/// </summary>
/// <param name="samples">The chunk samples.</param>
/// <param name="contextGenerator">The chunker context generator.</param>
public ChunkSampleSequenceStream(IObjectStream <ChunkSample> samples, IChunkerContextGenerator contextGenerator)
{
this.samples = samples;
this.contextGenerator = contextGenerator;
}
/// <summary>
/// Creates a chunker using the specified model and context generator and decodes the
/// model using a beam search of the specified size.
/// </summary>
/// <param name="model">
/// The maximum entropy model for this chunker.
/// </param>
/// <param name="contextGenerator">
/// The context generator to be used by the specified model.
/// </param>
/// <param name="beamSize">
/// The size of the beam that should be used when decoding sequences.
/// </param>
public MaximumEntropyChunker(MaxEntropyModel_Interface model, IChunkerContextGenerator contextGenerator, int beamSize)
{
mBeam = new ChunkBeamSearch(this, beamSize, contextGenerator, model);
mModel = model;
}
