de.jungblut.ner

Class IterativeSimilarityAggregation

java.lang.Object

de.jungblut.ner.IterativeSimilarityAggregation

public final class IterativeSimilarityAggregation
extends Object

Iterative similarity aggregation for named entity recognition and set expansion based on the paper "SEISA: Set Expansion by Iterative Similarity Aggregation". Those who wonder what the package name "ner" stands for, it is "named entity recognition".

Author:

thomas.jungblut

Constructor Summary

Constructors

Constructor and Description
IterativeSimilarityAggregation(String[] seedTokens, de.jungblut.math.tuple.Tuple<String[],de.jungblut.math.DoubleMatrix> bipartiteGraph) Constructs the similarity aggregation by seed tokens to expand and a given bipartite graph.
IterativeSimilarityAggregation(String[] seedTokens, de.jungblut.math.tuple.Tuple<String[],de.jungblut.math.DoubleMatrix> bipartiteGraph, double alpha, DistanceMeasurer distance) Constructs the similarity aggregation by seed tokens to expand and a given bipartite graph.

Method Summary

Modifier and Type	Method and Description
String[]	startStaticThresholding(double similarityThreshold, int maxIterations, boolean verbose) Starts the static thresholding algorithm and returns the expandedset of newly found related tokens.

Methods inherited from class java.lang.Object

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

Constructor Detail

IterativeSimilarityAggregation

public IterativeSimilarityAggregation(String[] seedTokens,
                                      de.jungblut.math.tuple.Tuple<String[],de.jungblut.math.DoubleMatrix> bipartiteGraph)

Constructs the similarity aggregation by seed tokens to expand and a given bipartite graph. The bipartite graph is represented as a two tuple, which consists of the vertices (called (candidate-) terms or entities) on the first item and the edges between those is a NxM matrix, where n is the entity tokens count and m is the number of the context vertices. Alpha is set to 0.5 and the cosine distance is used.

IterativeSimilarityAggregation

public IterativeSimilarityAggregation(String[] seedTokens,
                                      de.jungblut.math.tuple.Tuple<String[],de.jungblut.math.DoubleMatrix> bipartiteGraph,
                                      double alpha,
                                      DistanceMeasurer distance)

Constructs the similarity aggregation by seed tokens to expand and a given bipartite graph. The bipartite graph is represented as a three tuple, which consists of the vertices (called (candidate-) terms or entities) on the first item, the context vertices on the second item and the edges between those is a NxM matrix, where n is the entity tokens count and m is the number of the context vertices. Alpha is the constant weighting factor used throughout the paper (usually 0.5). The distance measurer to be used must be also defined.

Method Detail

startStaticThresholding

public String[] startStaticThresholding(double similarityThreshold,
                                        int maxIterations,
                                        boolean verbose)

Starts the static thresholding algorithm and returns the expandedset of newly found related tokens.

Parameters:

maxIterations - if > 0 the algorithm will stop after reached maxIterations.