Package network.aika.neuron.activation

Class SearchNode

java.lang.Object

network.aika.neuron.activation.SearchNode

All Implemented Interfaces:

java.lang.Comparable<SearchNode>

public class SearchNode
extends java.lang.Object
implements java.lang.Comparable<SearchNode>

The SearchNode class represents a node in the binary search tree that is used to find the optimal interpretation for a given document. Each search node possess a refinement (simply a set of interpretation nodes). The two options that this search node examines are that the refinement will either part of the final interpretation or not. During each search step the activation values in all the neuron activations adjusted such that they reflect the interpretation of the current search path. When the search reaches the maximum depth of the search tree and no further refinements exists, a weight is computed evaluating the current search path. The search path with the highest weight is used to determine the final interpretation.

Before the search is started a set of initial refinements is generated from the conflicts within the document. In other words, if there are no conflicts in a given document, then no search is needed. In this case the final interpretation will simply be the set of all interpretation nodes. The initial refinements are then expanded, meaning all interpretation nodes that are consistent with this refinement are added to the refinement. The initial refinements are then propagated along the search path as refinement candidates.

Author:

Lukas Molzberger

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	SearchNode.DebugState
static class	SearchNode.Decision
static interface	SearchNode.SkipSelectStep
static class	SearchNode.TimeoutException

Field Summary

Fields

Modifier and Type	Field	Description
static boolean	COMPUTE_SOFT_MAX
static boolean	ENABLE_CACHING
static int	MAX_SEARCH_STEPS
static boolean	OPTIMIZE_SEARCH

Constructor Summary

Constructors

Constructor	Description
SearchNode(Document doc, SearchNode selParent, SearchNode exclParent, int level)

Method Summary

Modifier and Type	Method	Description
void	changeState(Activation.Mode m)
boolean	compareNewState(SearchNode cachedNode)
int	compareTo(SearchNode sn)
static void	computeCachedFactor(SearchNode sn)
void	dumpDebugState()
double	getAccumulatedWeight()
Activation	getActivation()
SearchNode	getAlternative()
Activation.Option	getCurrentOption()
SearchNode.Decision	getDecision()
int	getId()
java.util.Map<Activation,Activation.StateChange>	getModifiedActivations()
Activation.Option	getOption()
SearchNode	getParent()
double	getWeightSum()
static void	invalidateCachedDecision(Activation act)
java.lang.String	pathToString()
static void	search(Document doc, SearchNode root, long v, java.lang.Long timeoutInMilliSeconds)	Searches for the best interpretation for the given document.
java.lang.String	toString()

Methods inherited from class java.lang.Object

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

Field Detail

MAX_SEARCH_STEPS

public static int MAX_SEARCH_STEPS

ENABLE_CACHING

public static boolean ENABLE_CACHING

OPTIMIZE_SEARCH

public static boolean OPTIMIZE_SEARCH

COMPUTE_SOFT_MAX

public static boolean COMPUTE_SOFT_MAX

Constructor Detail

SearchNode

public SearchNode(Document doc,
                  SearchNode selParent,
                  SearchNode exclParent,
                  int level)

Method Detail

getId

public int getId()

getOption

public Activation.Option getOption()

getModifiedActivations

public java.util.Map<Activation,Activation.StateChange> getModifiedActivations()

getAccumulatedWeight

public double getAccumulatedWeight()

getActivation

public Activation getActivation()

getCurrentOption

public Activation.Option getCurrentOption()

compareNewState

public boolean compareNewState(SearchNode cachedNode)

dumpDebugState

public void dumpDebugState()

search

public static void search(Document doc,
                          SearchNode root,
                          long v,
                          java.lang.Long timeoutInMilliSeconds)
                   throws SearchNode.TimeoutException

Searches for the best interpretation for the given document. This implementation of the algorithm is iterative to prevent stack overflow errors from happening. Depending on the document the search tree might be getting very deep.

Parameters:

doc -

root -

Throws:

SearchNode.TimeoutException

getWeightSum

public double getWeightSum()

getAlternative

public SearchNode getAlternative()

invalidateCachedDecision

public static void invalidateCachedDecision(Activation act)

computeCachedFactor

public static void computeCachedFactor(SearchNode sn)

pathToString

public java.lang.String pathToString()

toString

public java.lang.String toString()

Overrides:

toString in class java.lang.Object

changeState

public void changeState(Activation.Mode m)

compareTo

public int compareTo(SearchNode sn)

Specified by:

compareTo in interface java.lang.Comparable<SearchNode>

getParent

public SearchNode getParent()

getDecision

public SearchNode.Decision getDecision()