org.deeplearning4j.nlp.uima.corpora.treeparser

Class TreeParser

java.lang.Object

org.deeplearning4j.nlp.uima.corpora.treeparser.TreeParser

public class TreeParser
extends Object

Tree parser for constituency parsing

Author:

Adam Gibson

Constructor Summary

Constructors

Constructor and Description
TreeParser()
TreeParser(org.apache.uima.analysis_engine.AnalysisEngine parser, org.apache.uima.analysis_engine.AnalysisEngine tokenizer, org.apache.uima.util.CasPool pool)

Method Summary

Modifier and Type	Method and Description
static org.apache.uima.analysis_engine.AnalysisEngine	getParser()
static org.apache.uima.analysis_engine.AnalysisEngine	getTokenizer()
List<org.cleartk.syntax.constituent.type.TreebankNode>	getTreebankTrees(String text) Gets trees from text.
List<Tree>	getTrees(String text) Gets trees from text.
List<Tree>	getTrees(String text, SentencePreProcessor preProcessor) Gets trees from text.
List<Tree>	getTreesWithLabels(String text, List<String> labels) Gets trees from text.
List<Tree>	getTreesWithLabels(String text, String label, List<String> labels) Gets trees from text.

Methods inherited from class java.lang.Object

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

Constructor Detail

TreeParser

public TreeParser(org.apache.uima.analysis_engine.AnalysisEngine parser,
                  org.apache.uima.analysis_engine.AnalysisEngine tokenizer,
                  org.apache.uima.util.CasPool pool)

TreeParser

public TreeParser()
           throws Exception

Throws:

Exception

Method Detail

getTrees

public List<Tree> getTrees(String text,
                           SentencePreProcessor preProcessor)
                    throws Exception

Gets trees from text. First a sentence segmenter is used to segment the training examples in to sentences. Sentences are then turned in to trees and returned.

Parameters:

text - the text to process

preProcessor - the pre processor to use for pre processing sentences

Returns:

the list of trees

Throws:

Exception

getTreebankTrees

public List<org.cleartk.syntax.constituent.type.TreebankNode> getTreebankTrees(String text)
                                                                        throws Exception

Gets trees from text. First a sentence segmenter is used to segment the training examples in to sentences. Sentences are then turned in to trees and returned.

Parameters:

text - the text to process

Returns:

the list of trees

Throws:

Exception

getTreesWithLabels

public List<Tree> getTreesWithLabels(String text,
                                     String label,
                                     List<String> labels)
                              throws Exception

Gets trees from text. First a sentence segmenter is used to segment the training examples in to sentences. Sentences are then turned in to trees and returned. This will also process sentences with the following label format: some text This will allow you to iterate on and label sentences and label spans yourself.

Parameters:

text - the text to process

label - the label for the whole sentence

labels - the possible labels for the sentence

Returns:

the list of trees

Throws:

Exception

getTreesWithLabels

public List<Tree> getTreesWithLabels(String text,
                                     List<String> labels)
                              throws Exception

Gets trees from text. First a sentence segmenter is used to segment the training examples in to sentences. Sentences are then turned in to trees and returned. This will also process sentences with the following label format: some text This will allow you to iterate on and label sentences and label spans yourself.

Parameters:

text - the text to process

labels -

Returns:

the list of trees

Throws:

Exception

getTrees

public List<Tree> getTrees(String text)
                    throws Exception

Gets trees from text. First a sentence segmenter is used to segment the training examples in to sentences. Sentences are then turned in to trees and returned.

Parameters:

text - the text to process

Returns:

the list of trees

Throws:

Exception

getTokenizer

public static org.apache.uima.analysis_engine.AnalysisEngine getTokenizer()
                                                                   throws Exception

Throws:

Exception

getParser

public static org.apache.uima.analysis_engine.AnalysisEngine getParser()
                                                                throws Exception

Throws:

Exception