Package opennlp.dl.doccat

Class DocumentCategorizerDL

java.lang.Object

opennlp.dl.doccat.DocumentCategorizerDL

All Implemented Interfaces:

DocumentCategorizer

public class DocumentCategorizerDL
extends Object
implements DocumentCategorizer

An implementation of DocumentCategorizer that performs document classification using ONNX models.

Field Summary

Fields

Modifier and Type	Field	Description
static String	ATTENTION_MASK
static String	INPUT_IDS
static String	TOKEN_TYPE_IDS

Constructor Summary

Constructors

Constructor	Description
DocumentCategorizerDL(File model, File vocab, Map<Integer,String> categories, ClassificationScoringStrategy classificationScoringStrategy, InferenceOptions inferenceOptions)	Creates a new document categorizer using ONNX models.

Method Summary

Modifier and Type	Method	Description
double[]	categorize(String[] strings)
double[]	categorize(String[] strings, Map<String,Object> map)
String	getAllResults(double[] doubles)
String	getBestCategory(double[] doubles)
String	getCategory(int i)
int	getIndex(String s)
int	getNumberOfCategories()
Map<String,Double>	scoreMap(String[] strings)
SortedMap<Double,Set<String>>	sortedScoreMap(String[] strings)

Methods inherited from class java.lang.Object

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

Field Detail

INPUT_IDS

public static final String INPUT_IDS

See Also:

Constant Field Values

ATTENTION_MASK

public static final String ATTENTION_MASK

See Also:

Constant Field Values

TOKEN_TYPE_IDS

public static final String TOKEN_TYPE_IDS

See Also:

Constant Field Values

Constructor Detail

DocumentCategorizerDL

public DocumentCategorizerDL(File model,
                             File vocab,
                             Map<Integer,String> categories,
                             ClassificationScoringStrategy classificationScoringStrategy,
                             InferenceOptions inferenceOptions)
                      throws IOException,
                             ai.onnxruntime.OrtException

Creates a new document categorizer using ONNX models.

Parameters:

model - The ONNX model file.

vocab - The model's vocabulary file.

categories - The categories.

classificationScoringStrategy - Implementation of ClassificationScoringStrategy used to calculate the classification scores given the score of each individual document part.

inferenceOptions - InferenceOptions to control the inference.

Throws:

IOException

ai.onnxruntime.OrtException

Method Detail

categorize

public double[] categorize(String[] strings)

Specified by:

categorize in interface DocumentCategorizer

categorize

public double[] categorize(String[] strings,
                           Map<String,Object> map)

Specified by:

categorize in interface DocumentCategorizer

getBestCategory

public String getBestCategory(double[] doubles)

Specified by:

getBestCategory in interface DocumentCategorizer

getIndex

public int getIndex(String s)

Specified by:

getIndex in interface DocumentCategorizer

getCategory

public String getCategory(int i)

Specified by:

getCategory in interface DocumentCategorizer

getNumberOfCategories

public int getNumberOfCategories()

Specified by:

getNumberOfCategories in interface DocumentCategorizer

getAllResults

public String getAllResults(double[] doubles)

Specified by:

getAllResults in interface DocumentCategorizer

scoreMap

public Map<String,Double> scoreMap(String[] strings)

Specified by:

scoreMap in interface DocumentCategorizer

sortedScoreMap

public SortedMap<Double,Set<String>> sortedScoreMap(String[] strings)

Specified by:

sortedScoreMap in interface DocumentCategorizer