Utilizing neural networks for data anonymization

1. A method, comprising:

receiving, by a computer system, a natural language text;

producing, by a neural network, a numeric representation of the natural language text, wherein producing the numeric representation of the natural language text further comprises applying an irreversible distorting transformation to the numeric representation of the natural language text;

discarding the natural language text; and

performing, using the numeric representation of the natural language text, an information extraction task.

2. The method of claim 1 , wherein the neural network is an encoder part of an autoencoder.

3. The method of claim 1 , wherein applying to the numeric representation of the natural language text the irreversible distorting transformation further comprises:

adding, to each element of the numeric representation, a sample of a specified statistical distribution.

4. The method of claim 1 , wherein performing the information extraction task comprises:

using the numeric representation of the natural language text to determine that associating the natural language text was associated with a category of a predefined set of categories.

5. The method of claim 1 , wherein performing the information extraction task comprises:

evaluating a process that was characterized by the natural language text.

6. The method of claim 1 , wherein performing the information extraction task comprises:

evaluating a likelihood of occurrence of a specified event or condition.

7. The method of claim 1 , wherein performing the information extraction task comprises:

evaluating an emotional aspect that was present in the natural language text.

8. The method of claim 1 , wherein performing the information extraction task comprises:

feeding the numeric representation of the natural language text to a neural network that produces a numeric value indicative of a characteristic that was present in the natural language text.

9. A system, comprising:

a memory; and

a processor coupled to the memory, the processor configured to:

receive a natural language text;

transform, by a neural network, the natural language text into a numeric representation;

apply an irreversible distorting transformation to the numeric representation of the natural language text;

discard the natural language text; and

perform, using the numeric representation of the natural language text, an information extraction task.

10. The system of claim 9 , wherein the neural network is an encoder part of an autoencoder.

11. The system of claim 9 , wherein the processor being configured to perform the information extraction task comprises the processor being configured to:

use the numeric representation of the natural language text to determine that the natural language text was associated with a category of a predefined set of categories.

12. The system of claim 9 , wherein the processor being configured to perform the information extraction task comprises the processor being configured to:

evaluate a process that was characterized by the natural language text.

13. The system of claim 9 , wherein the processor being configured to perform the information extraction task comprises the processor being configured to:

evaluate a likelihood of occurrence of a specified event or condition.

14. The system of claim 9 , wherein the processor being configured to perform the information extraction task comprises the processor being configured to:

evaluate an emotional aspect that was present in the natural language text.

15. A non-transitory computer-readable storage medium comprising executable instructions that, when executed by a computer system, cause the computer system to:

receive a natural language text;

transform, by a neural network, the natural language text into a numeric representation;

apply an irreversible distorting transformation to the numeric representation of the natural language text;

discard the natural language text; and

perform, using the numeric representation of the natural language text, an information extraction task.

16. The non-transitory computer-readable storage medium of claim 15 , wherein the neural network is an encoder part of an autoencoder.

17. The non-transitory computer-readable storage medium of claim 15 , wherein the executable instructions that cause the computer system to perform the information extraction task further comprise executable instructions that, when executed by the computer system, cause the computer system to:

feed the numeric representation of the natural language text to a neural network that produces a numeric value indicative of a characteristic that was present in the natural language text.

18. The non-transitory computer-readable storage medium of claim 15 , wherein:

the neural network was trained, in part, using a decoder that was configured to decode respective training numeric representations into natural language text from a corpus of training text, and

the decoder is discarded after completing training of the neural network and prior to the computer system being caused to transform the natural language text into the numeric representation.

19. The non-transitory computer-readable storage medium of claim 15 , wherein the irreversible distorting transformation that is applied to the numeric representation is configured to thwart efforts directed to restoring the natural language text based on the numeric representation while preserving, in the numeric representation, semantic and other features extracted from the natural language text.

20. The system of claim 9 , wherein:

the neural network was trained, in part, using a decoder that was configured to decode respective training numeric representations into natural language text from a corpus of training text, and

the decoder is discarded after completing training of the neural network and prior to the transforming of the natural language text into the numeric representation.