Package opennlp.tools.chunker
Class ChunkerME
java.lang.Object
opennlp.tools.chunker.ChunkerME
- All Implemented Interfaces:
Chunker
The class represents a maximum-entropy-based
Chunker
. This chunker can be used to
find flat structures based on sequence inputs such as noun phrases or named entities.-
Field Summary
-
Constructor Summary
ConstructorDescriptionInitializes theChunker
by downloading a default model.ChunkerME
(ChunkerModel model) Initializes the current instance with the specifiedChunkerModel
. -
Method Summary
Modifier and TypeMethodDescriptionString[]
Generates chunk tags for the given sequence returning the result in an array.Span[]
chunkAsSpans
(String[] toks, String[] tags) Generates tagged chunk spans for the given sequence returning the result in a span array.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.Sequence[]
topKSequences
(String[] sentence, String[] tags) Returns the top k chunk sequences for the specified sentence with the specified pos-tagsSequence[]
topKSequences
(String[] sentence, String[] tags, double minSequenceScore) Returns the top k chunk sequences for the specified sentence with the specified pos-tagsstatic ChunkerModel
train
(String lang, ObjectStream<ChunkSample> in, TrainingParameters mlParams, ChunkerFactory factory) Starts a training of aChunkerModel
with the given parameters.
-
Field Details
-
DEFAULT_BEAM_SIZE
public static final int DEFAULT_BEAM_SIZE- See Also:
-
-
Constructor Details
-
ChunkerME
Initializes theChunker
by downloading a default model.- Parameters:
language
- The language of the model.- Throws:
IOException
- Thrown if the model cannot be downloaded or saved.
-
ChunkerME
Initializes the current instance with the specifiedChunkerModel
. TheDEFAULT_BEAM_SIZE
is used.- Parameters:
model
- A validmodel
instance.
-
-
Method Details
-
chunk
Description copied from interface:Chunker
Generates chunk tags for the given sequence returning the result in an array. -
chunkAsSpans
Description copied from interface:Chunker
Generates tagged chunk spans for the given sequence returning the result in a span array.- Specified by:
chunkAsSpans
in interfaceChunker
- Parameters:
toks
- an array of the tokens or words of the sequence.tags
- an array of the pos tags of the sequence.- Returns:
- an array of spans with chunk tags for each chunk in the sequence.
-
topKSequences
Description copied from interface:Chunker
Returns the top k chunk sequences for the specified sentence with the specified pos-tags- Specified by:
topKSequences
in interfaceChunker
- Parameters:
sentence
- The tokens of the sentence.tags
- The pos-tags for the specified sentence.- Returns:
- the top k chunk sequences for the specified sentence.
-
topKSequences
Description copied from interface:Chunker
Returns the top k chunk sequences for the specified sentence with the specified pos-tags- Specified by:
topKSequences
in interfaceChunker
- Parameters:
sentence
- The tokens of the sentence.tags
- The pos-tags for the specified sentence.minSequenceScore
- A lower bound on the score of a returned sequence.- Returns:
- the top k chunk sequences for the specified sentence.
-
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 tochunk
. The specified array should be at least as large as the number of tokens in the previous call tochunk
.- 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 tochunk
.- Returns:
- An array with the same number of probabilities as tokens when
chunk(String[], String[])
was last called.
-
train
public static ChunkerModel train(String lang, ObjectStream<ChunkSample> in, TrainingParameters mlParams, ChunkerFactory factory) throws IOException Starts a training of aChunkerModel
with the given parameters.- Parameters:
lang
- The ISO conform language code.in
- TheObjectStream
ofChunkSample
used as input for training.mlParams
- TheTrainingParameters
for the context of the training.factory
- TheChunkerFactory
for creating related objects defined viamlParams
.- Returns:
- A valid, trained
ChunkerModel
instance. - Throws:
IOException
- Thrown if IO errors occurred.
-