edu.stanford.nlp.coref.statistical

Class Clusterer

java.lang.Object

edu.stanford.nlp.coref.statistical.Clusterer

public class Clusterer
extends java.lang.Object

System for building up coreference clusters incrementally, merging a pair of clusters each step. Trained with a variant of the SEARN imitation learning algorithm.

Author:

Kevin Clark

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	Clusterer.Cluster

Field Summary

Fields

Modifier and Type	Field and Description
static int	currentDocId
static int	isTraining

Constructor Summary

Constructors

Constructor and Description
Clusterer()
Clusterer(java.lang.String modelPath)

Method Summary

Modifier and Type	Method and Description
void	doTraining(java.lang.String modelName)
java.util.List<Pair<java.lang.Integer,java.lang.Integer>>	getClusterMerges(ClustererDataLoader.ClustererDoc doc)

Methods inherited from class java.lang.Object

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

Field Detail

currentDocId

public static int currentDocId

isTraining

public static int isTraining

Constructor Detail

Clusterer

public Clusterer()

Clusterer

public Clusterer(java.lang.String modelPath)

Method Detail

getClusterMerges

public java.util.List<Pair<java.lang.Integer,java.lang.Integer>> getClusterMerges(ClustererDataLoader.ClustererDoc doc)

doTraining

public void doTraining(java.lang.String modelName)