edu.illinois.cs.cogcomp.pos

Class POSBaselineLearner

java.lang.Object

edu.illinois.cs.cogcomp.lbjava.classify.Classifier

edu.illinois.cs.cogcomp.lbjava.learn.Learner

edu.illinois.cs.cogcomp.pos.POSBaselineLearner

All Implemented Interfaces:

Serializable, Cloneable

Direct Known Subclasses:

BaselineTarget, MikheevLearner

public class POSBaselineLearner
extends edu.illinois.cs.cogcomp.lbjava.learn.Learner

This learning algorithm simply counts the number of times that each word appears in training data associated with each possible part of speech tag. It assumes that its feature extractor classifier is discrete, i.e. that in the LBJ source file, a single discrete classifier is named in the learning classifier expression's using clause. That classifier is assumed to return the form of the word.

Note: This learner will not work if feature pre-extraction is enabled for it.

Author:

Nick Rizzolo

See Also:

Serialized Form

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	POSBaselineLearner.Parameters Empty class, since there are no parameters

Field Summary

Fields

Modifier and Type	Field and Description
protected HashMap<String,TreeMap<String,Integer>>	table This map associates words with maps that associate POS tags with counts.

Fields inherited from class edu.illinois.cs.cogcomp.lbjava.learn.Learner

candidates, encoding, extractor, labeler, labelLexicon, lcFilePath, lexFilePath, lexicon, lossFlag, predictions, readLexiconOnDemand

Fields inherited from class edu.illinois.cs.cogcomp.lbjava.classify.Classifier

containingPackage, name

Constructor Summary

Constructors

Constructor and Description
POSBaselineLearner() Default constructor; sets the name to the empty string.
POSBaselineLearner(POSBaselineLearner.Parameters p) Does nothing, as there are not parameters.
POSBaselineLearner(String n) Constructor setting the name of the classifier.

Method Summary

Modifier and Type	Method and Description
Set<String>	allowableTags(String form) Returns the set of tags that the given word has been observed with.
edu.illinois.cs.cogcomp.lbjava.classify.FeatureVector	classify(int[] exampleFeatures, double[] exampleValues) Dummy implementation of the abstract learn(int[],double[],int[],double[]) signature for the compiler.
edu.illinois.cs.cogcomp.lbjava.classify.FeatureVector	classify(Object example) This function makes one or more decisions about a single object, returning those decisions as Features in a vector.
protected String	computePrediction(Object example) Computes the prediction for this example.
String	discreteValue(Object example) Returns the value of the discrete prediction that this learner would make, given an example.
edu.illinois.cs.cogcomp.lbjava.learn.Learner	emptyClone() Returns a new, emtpy learner into which all of the parameters that control the behavior of the algorithm have been copied.
edu.illinois.cs.cogcomp.lbjava.classify.Feature	featureValue(Object example) Returns the classification of the given example object as a single feature instead of a FeatureVector.
void	forget() Clears out the table to start fresh.
String	getInputType() Returns a string describing the input type of this classifier.
void	learn(int[] exampleFeatures, double[] exampleValues, int[] exampleLabels, double[] labelValues) Dummy implementation of the abstract learn(int[],double[],int[],double[]) signature for the compiler.
void	learn(Object example) Trains the learning algorithm given an object as an example.
static boolean	looksLikeNumber(String form) Determines if the input word looks like a number of some sort.
boolean	observed(String form) Indicates whether the input word was observed while training this learner.
int	observedCount(String form) Returns the number of times the given form has been observed.
void	read(ExceptionlessInputStream in) Reads the binary representation of a learner with this object's run-time type, overwriting any and all learned or manually specified parameters as well as the label lexicon but without modifying the feature lexicon.
protected static void	read(ExceptionlessInputStream in, HashMap<String,TreeMap<String,Integer>> map) Reads in the binary representation of the specific form of map used by this class.
edu.illinois.cs.cogcomp.lbjava.classify.ScoreSet	scores(int[] features, double[] values) Returns null.
void	write(ExceptionlessOutputStream out) Writes the learned function's internal representation in binary form.
protected static void	write(ExceptionlessOutputStream out, HashMap<String,TreeMap<String,Integer>> map) Writes the binary representation of the specific form of map used by this class.
void	write(PrintStream out) Writes the algorithm's internal representation as text.
static void	write(PrintStream out, HashMap<String,TreeMap<String,Integer>> table) Writes the algorithm's internal representation as text.

Methods inherited from class edu.illinois.cs.cogcomp.lbjava.learn.Learner

classify, classify, classify, clone, countFeatures, createPrediction, createPrediction, demandLexicon, discreteValue, discreteValue, doneLearning, doneWithRound, featureValue, featureValue, getCurrentLexicon, getExampleArray, getExampleArray, getExtractor, getLabeler, getLabelLexicon, getLexicon, getLexiconDiscardCounts, getLexiconLocation, getModelLocation, getParameters, getPrunedLexiconSize, initialize, learn, learn, learn, read, readLabelLexicon, readLearner, readLearner, readLearner, readLearner, readLearner, readLearner, readLexicon, readLexicon, readLexiconOnDemand, readLexiconOnDemand, readModel, readModel, readParameters, realValue, realValue, realValue, save, saveLexicon, saveModel, scores, scores, scoresAugmented, setCandidates, setEncoding, setExtractor, setLabeler, setLabelLexicon, setLexicon, setLexiconLocation, setLexiconLocation, setLossFlag, setModelLocation, setModelLocation, setParameters, setReadLexiconOnDemand, unclone, unsetLossFlag, write, writeLexicon, writeModel, writeParameters

Methods inherited from class edu.illinois.cs.cogcomp.lbjava.classify.Classifier

allowableValues, classify, discreteValueArray, getCompositeChildren, getOutputType, realValueArray, test, toString, valueIndexOf

Methods inherited from class java.lang.Object

equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

Field Detail

table

protected HashMap<String,TreeMap<String,Integer>> table

This map associates words with maps that associate POS tags with counts.

Constructor Detail

POSBaselineLearner

public POSBaselineLearner()

Default constructor; sets the name to the empty string.

POSBaselineLearner

public POSBaselineLearner(String n)

Constructor setting the name of the classifier.

Parameters:

n - The name of the classifier.

POSBaselineLearner

public POSBaselineLearner(POSBaselineLearner.Parameters p)

Does nothing, as there are not parameters.

Method Detail

emptyClone

public edu.illinois.cs.cogcomp.lbjava.learn.Learner emptyClone()

Returns a new, emtpy learner into which all of the parameters that control the behavior of the algorithm have been copied. Here, "emtpy" means no learning has taken place.

Overrides:

emptyClone in class edu.illinois.cs.cogcomp.lbjava.learn.Learner

getInputType

public String getInputType()

Returns a string describing the input type of this classifier.

Overrides:

getInputType in class edu.illinois.cs.cogcomp.lbjava.classify.Classifier

Returns:

"edu.illinois.cs.cogcomp.lbjava.nlp.Word"

learn

public void learn(Object example)

Trains the learning algorithm given an object as an example.

Overrides:

learn in class edu.illinois.cs.cogcomp.lbjava.learn.Learner

Parameters:

example - An example of the desired learned classifier's behavior.

learn

public void learn(int[] exampleFeatures,
                  double[] exampleValues,
                  int[] exampleLabels,
                  double[] labelValues)

Dummy implementation of the abstract learn(int[],double[],int[],double[]) signature for the compiler. Not to be used by the programmer.

Specified by:

learn in class edu.illinois.cs.cogcomp.lbjava.learn.Learner

Parameters:

exampleFeatures - Not used.

exampleValues - Not used.

exampleLabels - Not used.

labelValues - Not used.

forget

public void forget()

Clears out the table to start fresh.

Overrides:

forget in class edu.illinois.cs.cogcomp.lbjava.learn.Learner

looksLikeNumber

public static boolean looksLikeNumber(String form)

Determines if the input word looks like a number of some sort.

Parameters:

form - The form of the word.

Returns:

true iff the word contains only characters in ".,-" and at least one digit.

discreteValue

public String discreteValue(Object example)

Returns the value of the discrete prediction that this learner would make, given an example.

Overrides:

discreteValue in class edu.illinois.cs.cogcomp.lbjava.learn.Learner

Parameters:

example - The example object.

Returns:

The discrete value.

computePrediction

protected String computePrediction(Object example)

Computes the prediction for this example. This method only exists because of the way that generated code calls discreteValue(Object), featureValue(Object), and classify(Object).

Parameters:

example - The example object.

Returns:

The discrete value.

featureValue

public edu.illinois.cs.cogcomp.lbjava.classify.Feature featureValue(Object example)

Returns the classification of the given example object as a single feature instead of a FeatureVector.

Overrides:

featureValue in class edu.illinois.cs.cogcomp.lbjava.learn.Learner

Parameters:

example - The object to classify.

Returns:

The classification of example as a feature.

classify

public edu.illinois.cs.cogcomp.lbjava.classify.FeatureVector classify(Object example)

This function makes one or more decisions about a single object, returning those decisions as Features in a vector.

Overrides:

classify in class edu.illinois.cs.cogcomp.lbjava.learn.Learner

Parameters:

example - The object to make decisions about.

Returns:

A vector of Features about the input object.

classify

public edu.illinois.cs.cogcomp.lbjava.classify.FeatureVector classify(int[] exampleFeatures,
                                                                      double[] exampleValues)

Dummy implementation of the abstract learn(int[],double[],int[],double[]) signature for the compiler. Not to be used by the programmer.

Specified by:

classify in class edu.illinois.cs.cogcomp.lbjava.learn.Learner

Parameters:

exampleFeatures - Not used.

exampleValues - Not used.

Returns:

An empty feature vector.

scores

public edu.illinois.cs.cogcomp.lbjava.classify.ScoreSet scores(int[] features,
                                                               double[] values)

Returns null.

Specified by:

scores in class edu.illinois.cs.cogcomp.lbjava.learn.Learner

observed

public boolean observed(String form)

Indicates whether the input word was observed while training this learner.

Parameters:

form - The form of the word.

Returns:

true if this learner contains statistics for the input word.

observedCount

public int observedCount(String form)

Returns the number of times the given form has been observed.

allowableTags

public Set<String> allowableTags(String form)

Returns the set of tags that the given word has been observed with.

Parameters:

form - The form of the word.

Returns:

The set of tags observed in association with the given word.

write

public void write(PrintStream out)

Writes the algorithm's internal representation as text.

Specified by:

write in class edu.illinois.cs.cogcomp.lbjava.learn.Learner

Parameters:

out - The output stream.

write

public static void write(PrintStream out,
                         HashMap<String,TreeMap<String,Integer>> table)

Writes the algorithm's internal representation as text.

Parameters:

out - The output stream.

table - The table.

write

public void write(ExceptionlessOutputStream out)

Writes the learned function's internal representation in binary form.

Overrides:

write in class edu.illinois.cs.cogcomp.lbjava.learn.Learner

Parameters:

out - The output stream.

write

protected static void write(ExceptionlessOutputStream out,
                            HashMap<String,TreeMap<String,Integer>> map)

Writes the binary representation of the specific form of map used by this class.

Parameters:

out - The output stream.

map - The map to write.

read

public void read(ExceptionlessInputStream in)

Reads the binary representation of a learner with this object's run-time type, overwriting any and all learned or manually specified parameters as well as the label lexicon but without modifying the feature lexicon.

Overrides:

read in class edu.illinois.cs.cogcomp.lbjava.learn.Learner

Parameters:

in - The input stream.

read

protected static void read(ExceptionlessInputStream in,
                           HashMap<String,TreeMap<String,Integer>> map)

Reads in the binary representation of the specific form of map used by this class.

Parameters:

in - The input stream.

map - The map to read into.