edu.ucla.sspace.wordsi.semeval

Class SemEvalDependencyContextExtractor

java.lang.Object

edu.ucla.sspace.wordsi.DependencyContextExtractor

edu.ucla.sspace.wordsi.semeval.SemEvalDependencyContextExtractor

All Implemented Interfaces:

ContextExtractor

public class SemEvalDependencyContextExtractor
extends DependencyContextExtractor

A SenseEval/SemEval based DependencyContextExtractor. This extractor assumes that the instance id is the first line in the document and that each document only contains the sentences for that instance id. The dependency tree node for the focus word of each context should match the instance id. The primary key will be the raw token of the instance id and the secondary key will be the instance id.

Author:

Keith Stevens

Field Summary

Fields inherited from class edu.ucla.sspace.wordsi.DependencyContextExtractor

extractor, generator, readHeader

Constructor Summary

Constructors

Constructor and Description
SemEvalDependencyContextExtractor(DependencyExtractor extractor, DependencyContextGenerator generator) Creates a new SemEvalDependencyContextExtractor.

Method Summary

Methods

Modifier and Type	Method and Description
protected boolean	acceptWord(DependencyTreeNode focusNode, String contextHeader, Wordsi wordsi) Returns true if the focusWord equals the contextHeader.
protected String	getSecondaryKey(DependencyTreeNode focusNode, String contextHeader) Returns the word of the focusNode

Methods inherited from class edu.ucla.sspace.wordsi.DependencyContextExtractor

getPrimaryKey, getVectorLength, handleContextHeader, processDocument

Methods inherited from class java.lang.Object

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

Constructor Detail

SemEvalDependencyContextExtractor

public SemEvalDependencyContextExtractor(DependencyExtractor extractor,
                                 DependencyContextGenerator generator)

Creates a new SemEvalDependencyContextExtractor.

Parameters:

extractor - The DependencyExtractor that parses the document and returns a valid dependency tree

basisMapping - A mapping from dependency paths to feature indices

weighter - A weighting function for dependency paths

acceptor - An accepting function that validates dependency paths which may serve as features

Method Detail

acceptWord

protected boolean acceptWord(DependencyTreeNode focusNode,
                 String contextHeader,
                 Wordsi wordsi)

Returns true if the focusWord equals the contextHeader.

Overrides:

acceptWord in class DependencyContextExtractor

getSecondaryKey

protected String getSecondaryKey(DependencyTreeNode focusNode,
                     String contextHeader)

Returns the word of the focusNode

Overrides:

getSecondaryKey in class DependencyContextExtractor