Joshua
open source statistical hierarchical phrase-based machine translation system
 All Classes Namespaces Functions Variables Typedefs Enumerations Enumerator Friends
joshua.decoder.hypergraph.HyperEdge Class Reference
Inheritance diagram for joshua.decoder.hypergraph.HyperEdge:
[legend]
Collaboration diagram for joshua.decoder.hypergraph.HyperEdge:
[legend]

List of all members.

Public Member Functions

 HyperEdge (Rule rule, double bestDerivationLogP, Double transitionLogP, List< HGNode > antNodes, SourcePath srcPath)
Rule getRule ()
SourcePath getSourcePath ()
List< HGNodegetAntNodes ()
double getTransitionLogP (boolean forceCompute)
void setTransitionLogP (double transitionLogP)

Public Attributes

double bestDerivationLogP = Double.NEGATIVE_INFINITY

Private Attributes

Double transitionLogP = null
Rule rule
SourcePath srcPath = null
List< HGNodeantNodes = null

Detailed Description

this class implement Hyperedge

Author:
Zhifei Li, zhife.nosp@m.i.wo.nosp@m.rk@gm.nosp@m.ail..nosp@m.com
Version:
$LastChangedDate$

Constructor & Destructor Documentation

joshua.decoder.hypergraph.HyperEdge.HyperEdge ( Rule  rule,
double  bestDerivationLogP,
Double  transitionLogP,
List< HGNode antNodes,
SourcePath  srcPath 
)

Member Function Documentation

Here is the caller graph for this function:

Here is the caller graph for this function:

Here is the caller graph for this function:

Here is the caller graph for this function:


Member Data Documentation

If antNodes is null, then this edge corresponds to a rule with zero arity. Aslo, the nodes appear in the list as per the index of the Foreign side non-terminal

double joshua.decoder.hypergraph.HyperEdge.bestDerivationLogP = Double.NEGATIVE_INFINITY

the 1-best logP of all possible derivations: best logP of ant hgnodes + transitionlogP

this remembers the stateless + non_stateless logP assocated with the rule (excluding the best-logP from ant nodes)