public MaximumEntropyPOSTagger(int beamSize, MaxEntropyModel_Interface model, IPosContextGenerator contextGenerator, Interfaces.PosLookupList dictionary)
{
mBeamSize = beamSize;
mPosModel = model;
mContextGenerator = contextGenerator;
Beam = new PosBeamSearch(this, mBeamSize, contextGenerator, model);
mDictionary = dictionary;
}
/// <summary>
/// Creates new search object.
/// </summary>
/// <param name="size">
/// The size of the beam (k).
/// </param>
/// <param name="contextGenerator">
/// the context generator for the model.
/// </param>
/// <param name="model">
/// the model for assigning probabilities to the sequence outcomes.
/// </param>
/// <param name="cacheSize">
/// size of the cache to use for performance.
/// </param>
public BeamSearch(int size, IBeamSearchContextGenerator contextGenerator, MaxEntropyModel_Interface model, int cacheSize)
{
Size = size;
ContextGenerator = contextGenerator;
Model = model;
mProbabilities = new double[model.OutcomeCount];
if (cacheSize > 0)
{
mContextsCache = new Cache(cacheSize);
}
}
public virtual void LocalEvaluate(MaxEntropyModel_Interface posModel, System.IO.StreamReader reader, out double accuracy, out double sentenceAccuracy)
{
mPosModel = posModel;
float total = 0, correct = 0, sentences = 0, sentencesCorrect = 0;
System.IO.StreamReader sentenceReader = new System.IO.StreamReader(reader.BaseStream, System.Text.Encoding.UTF7);
string line;
while ((object)(line = sentenceReader.ReadLine()) != null)
{
sentences++;
Util.Pair <ArrayList, ArrayList> annotatedPair = Interfaces.PosEventReader.ConvertAnnotatedString(line);
ArrayList words = annotatedPair.FirstValue;
ArrayList outcomes = annotatedPair.SecondValue;
ArrayList tags = new ArrayList(Beam.BestSequence(words, null).Outcomes);
int count = 0;
bool isSentenceOK = true;
for (System.Collections.IEnumerator tagIndex = tags.GetEnumerator(); tagIndex.MoveNext(); count++)
{
total++;
string tag = (string)tagIndex.Current;
if (tag == (string)outcomes[count])
{
correct++;
}
else
{
isSentenceOK = false;
}
}
if (isSentenceOK)
{
sentencesCorrect++;
}
}
accuracy = correct / total;
sentenceAccuracy = sentencesCorrect / sentences;
}
/// <summary>
/// Creates a new name finder with the specified model and context generator.
/// </summary>
/// <param name="model">
/// The model to be used to find names.
/// </param>
/// <param name="contextGenerator">
/// The context generator to be used with this name finder.
/// </param>
/// <param name="beamSize">
/// The size of the beam to be used in decoding this model.
/// </param>
public MaximumEntropyNameFinder(MaxEntropyModel_Interface model, Interfaces.INameContextGenerator contextGenerator, int beamSize)
{
mModel = model;
mContextGenerator = contextGenerator;
mBeam = new NameBeamSearch(this, beamSize, contextGenerator, model, beamSize);
}
/// <summary>
/// Creates a new name finder with the specified model and context generator.
/// </summary>
/// <param name="model">
/// The model to be used to find names.
/// </param>
/// <param name="contextGenerator">
/// The context generator to be used with this name finder.
/// </param>
public MaximumEntropyNameFinder(MaxEntropyModel_Interface model, Interfaces.INameContextGenerator contextGenerator) : this(model, contextGenerator, 10)
{
}
/// <summary>
/// Creates a new name finder with the specified model.
/// </summary>
/// <param name="model">
/// The model to be used to find names.
/// </param>
public MaximumEntropyNameFinder(MaxEntropyModel_Interface model) : this(model, new Interfaces.DefaultNameContextGenerator(10), 10)
{
}
/// <summary>
/// Creates a beam seach of the specified size using the specified model with the specified context generator.
/// </summary>
/// <param name="nameFinder">
/// The associated MaximumEntropyNameFinder instance.
/// </param>
/// <param name="size">
/// The size of the beam.
/// </param>
/// <param name="contextGenerator">
/// The context generator used with the specified model.
/// </param>
/// <param name="model">
/// The model used to determine names.
/// </param>
/// <param name="beamSize">
/// The size of the beam to use in searching.
/// </param>
public NameBeamSearch(MaximumEntropyNameFinder nameFinder, int size, Interfaces.INameContextGenerator contextGenerator, MaxEntropyModel_Interface model, int beamSize) : base(size, contextGenerator, model, beamSize)
{
mNameFinder = nameFinder;
}
public PosBeamSearch(MaximumEntropyPOSTagger posTagger, int size, Util.IBeamSearchContextGenerator contextGenerator, MaxEntropyModel_Interface model, int cacheSize) : base(size, contextGenerator, model, cacheSize)
{
mMaxentPosTagger = posTagger;
}
public MaximumEntropyPOSTagger(MaxEntropyModel_Interface model, IPosContextGenerator contextGenerator, Interfaces.PosLookupList dictionary) : this(mDefaultBeamSize, model, contextGenerator, dictionary)
{
}
public MaximumEntropyPOSTagger(MaxEntropyModel_Interface model, IPosContextGenerator contextGenerator) : this(mDefaultBeamSize, model, contextGenerator, null)
{
}
// Constructors
public MaximumEntropyPOSTagger(MaxEntropyModel_Interface model) : this(model, new POS_ContextGenerator())
{
}
/// <summary>
/// Creates new search object.
/// </summary>
/// <param name="size">
/// The size of the beam (k).
/// </param>
/// <param name="contextGenerator">
/// the context generator for the model.
/// </param>
/// <param name="model">
/// the model for assigning probabilities to the sequence outcomes.
/// </param>
public BeamSearch(int size, IBeamSearchContextGenerator contextGenerator, MaxEntropyModel_Interface model) : this(size, contextGenerator, model, 0)
{
}
/// <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>
/// Creates a chunker using the specified model.
/// </summary>
/// <param name="model">
/// The maximum entropy model for this chunker.
/// </param>
public MaximumEntropyChunker(MaxEntropyModel_Interface model):this(model, new DefaultChunkerContextGenerator(), 10)
{
}
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 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;
}