org.deeplearning4j.text.inputsanitation

Class InputHomogenization

java.lang.Object

org.deeplearning4j.text.inputsanitation.InputHomogenization

public class InputHomogenization
extends java.lang.Object

Performs some very basic textual transformations such as word shape, lower casing, and stripping of punctuation

Constructor Summary

Constructors

Constructor and Description
InputHomogenization(java.lang.String input) Input text to applyTransformToOrigin
InputHomogenization(java.lang.String input, boolean preserveCase)
InputHomogenization(java.lang.String input, java.util.List<java.lang.String> ignoreCharactersContaining)

Method Summary

Modifier and Type	Method and Description
java.lang.String	transform() Returns the normalized text passed in via constructor

Methods inherited from class java.lang.Object

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

Constructor Detail

InputHomogenization

public InputHomogenization(java.lang.String input)

Input text to applyTransformToOrigin

Parameters:

input - the input text to applyTransformToOrigin, equivalent to calling this(input,false) wrt preserving case

InputHomogenization

public InputHomogenization(java.lang.String input,
                           boolean preserveCase)

Parameters:

input - the input to applyTransformToOrigin

preserveCase - whether to preserve case

InputHomogenization

public InputHomogenization(java.lang.String input,
                           java.util.List<java.lang.String> ignoreCharactersContaining)

Parameters:

input - the input to applyTransformToOrigin

ignoreCharactersContaining - ignore transformation of words containigng specified strings

Method Detail

transform

public java.lang.String transform()

Returns the normalized text passed in via constructor

Returns:

the normalized text passed in via constructor