eus.ixa.ixa.pipe.ml.sequence

Class SequenceLabelerME

java.lang.Object

eus.ixa.ixa.pipe.ml.sequence.SequenceLabelerME

All Implemented Interfaces:

SequenceLabeler

public class SequenceLabelerME
extends Object
implements SequenceLabeler

Field Summary

Fields

Modifier and Type	Field and Description
protected SequenceLabelerContextGenerator	contextGenerator
static Pattern	contPattern
static int	DEFAULT_BEAM_SIZE
static Pattern	lastPattern
protected opennlp.tools.ml.model.SequenceClassificationModel<String>	model
static Pattern	otherPattern
static Pattern	startPattern
static Pattern	unitPattern

Constructor Summary

Constructors

Constructor and Description
SequenceLabelerME(SequenceLabelerModel model)

Method Summary

Modifier and Type	Method and Description
void	clearAdaptiveData() Forgets all adaptive data which was collected during previous calls to one of the find methods.
String[]	decodeSequences(String[] preds) Decode Sequences from an array of Strings.
static Span[]	dropOverlappingSpans(Span[] spans) Removes spans with are intersecting or crossing in anyway.
double[]	probs() Returns an array with the probabilities of the last decoded sequence.
void	probs(double[] probs) Populates the specified array with the probabilities of the last decoded sequence.
double[]	probs(Span[] spans) Returns an array of probabilities for each of the specified spans which is the arithmetic mean of the probabilities for each of the outcomes which make up the span.
Span[][]	tag(int numTaggings, String[] tokens) Returns at most the specified number of taggings for the specified sentence.
Span[]	tag(String[] tokens) Generates tags for the given sequence, typically a sentence, returning token spans for any identified sequences.
Span[]	tag(String[] tokens, String[][] additionalContext) Generates sequence tags for the given sequence, returning spans for any identified sequences.
String[]	tagToStrings(String[] tokens)
opennlp.tools.util.Sequence[]	topKSequences(String[] tokens)
opennlp.tools.util.Sequence[]	topKSequences(String[] tokens, String[] tags, double minSequenceScore)
static SequenceLabelerModel	train(String languageCode, String type, opennlp.tools.util.ObjectStream<SequenceLabelSample> samples, opennlp.tools.util.TrainingParameters trainParams, SequenceLabelerFactory factory)

Methods inherited from class java.lang.Object

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

Field Detail

DEFAULT_BEAM_SIZE

public static final int DEFAULT_BEAM_SIZE

See Also:

Constant Field Values

startPattern

public static Pattern startPattern

contPattern

public static Pattern contPattern

lastPattern

public static Pattern lastPattern

unitPattern

public static Pattern unitPattern

otherPattern

public static Pattern otherPattern

model

protected opennlp.tools.ml.model.SequenceClassificationModel<String> model

contextGenerator

protected SequenceLabelerContextGenerator contextGenerator

Constructor Detail

SequenceLabelerME

public SequenceLabelerME(SequenceLabelerModel model)

Method Detail

tag

public Span[] tag(String[] tokens)

Description copied from interface: SequenceLabeler

Generates tags for the given sequence, typically a sentence, returning token spans for any identified sequences.

Specified by:

tag in interface SequenceLabeler

Parameters:

tokens - an array of the tokens or words of the sequence, typically a sentence.

Returns:

an array of spans for each of the sequences identified.

tag

public Span[] tag(String[] tokens,
                  String[][] additionalContext)

Generates sequence tags for the given sequence, returning spans for any identified sequences.

Parameters:

tokens - an array of the tokens or words, typically a sentence.

additionalContext - features which are based on context outside of the sentence but which should also be used.

Returns:

an array of spans for each of the names identified.

tagToStrings

public String[] tagToStrings(String[] tokens)

tag

public Span[][] tag(int numTaggings,
                    String[] tokens)

Returns at most the specified number of taggings for the specified sentence.

Parameters:

numTaggings - the number of labels to be returned.

tokens - an array of tokens which make up a sentence.

Returns:

at most the specified number of labels for the specified sentence.

topKSequences

public opennlp.tools.util.Sequence[] topKSequences(String[] tokens)

topKSequences

public opennlp.tools.util.Sequence[] topKSequences(String[] tokens,
                                                   String[] tags,
                                                   double minSequenceScore)

clearAdaptiveData

public void clearAdaptiveData()

Forgets all adaptive data which was collected during previous calls to one of the find methods. This method is typical called at the end of a document.

Specified by:

clearAdaptiveData in interface SequenceLabeler

probs

public void probs(double[] probs)

Populates the specified array with the probabilities of the last decoded sequence. The sequence was determined based on the previous call to chunk. The specified array should be at least as large as the number of tokens in the previous call to chunk.

Parameters:

probs - An array used to hold the probabilities of the last decoded sequence.

probs

public double[] probs()

Returns an array with the probabilities of the last decoded sequence. The sequence was determined based on the previous call to chunk.

Returns:

An array with the same number of probabilities as tokens were sent to chunk when it was last called.

probs

public double[] probs(Span[] spans)

Returns an array of probabilities for each of the specified spans which is the arithmetic mean of the probabilities for each of the outcomes which make up the span.

Parameters:

spans - The spans of the names for which probabilities are desired.

Returns:

an array of probabilities for each of the specified spans.

train

public static SequenceLabelerModel train(String languageCode,
                                         String type,
                                         opennlp.tools.util.ObjectStream<SequenceLabelSample> samples,
                                         opennlp.tools.util.TrainingParameters trainParams,
                                         SequenceLabelerFactory factory)
                                  throws IOException

Throws:

IOException

dropOverlappingSpans

public static Span[] dropOverlappingSpans(Span[] spans)

Removes spans with are intersecting or crossing in anyway.

The following rules are used to remove the spans:
Identical spans: The first span in the array after sorting it remains
Intersecting spans: The first span after sorting remains
Contained spans: All spans which are contained by another are removed

Parameters:

spans - the spans

Returns:

non-overlapping spans

decodeSequences

public String[] decodeSequences(String[] preds)

Decode Sequences from an array of Strings.

Parameters:

preds - the sequences in an string array.

Returns:

the decoded sequences