Natural language processor for providing natural language signals in a natural language output

• US 10,394,861 B2
• Filed: 10/22/2015
• Issued: 08/27/2019
• Est. Priority Date: 10/22/2015
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Erickson, Thomas D., Farrell, Robert G.
• Primary Examiner(s): Jackson, Jakieda R
• Application Number:
  US14/920,131
• Publication Number:
  US 20170116187A1
• Time in Patent Office: Days
• Field of Search: 704 9, 704 2
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 16/3332 Query translation
• CPC Class Codes: G06F 16/345 Summarisation for human users
• CPC Class Codes: G06F 40/253 Grammatical analysis; Style critique
• CPC Class Codes: G06F 40/58 Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
• CPC Class Codes: G10L 13/027 Concept to speech synthesisers; Generation of natural phrases from machine-based concepts generation of parameters for speech synthesis out of text G10L13/08
• CPC Class Codes: G10L 13/10 Prosody rules derived from text; Stress or intonation

Abstract

Embodiments are directed to a natural language processing (NLP) system configured to receive a natural language (NL) input and perform an analysis operation to generate a NL output. The NLP system is configured to generate at least one confidence level based at least in part on at least one portion of the analysis operation. The NLP system is further configured to integrate at least one disfluency into the NL output based at least in part on the at least one confidence level.

Claims

1. A speech synthesis (SS) system configured to convert natural language inputs to natural language outputs and provide a natural language alert that communicates that the natural language outputs may contain error, the SS system comprising:

a memory having disfluency natural language data stored therein; and

a processor-based input/output module system communicatively coupled to the memory;

wherein the input/output module comprises a natural language input module communicatively coupled to a machine translation module;

wherein the input/output module further comprises a natural language output module communicatively coupled to the machine translation module;

wherein the input/output module is configured to;

receive, using the natural language input module, a natural language input;

convert, using the natural language input module, the natural language input to natural language input data;

perform, using the machine translation module, a natural language analysis operation on the natural language input data to generate natural language output data;

wherein the natural language analysis operation comprises performing a confidence level analysis on at least one portion of the natural language analysis operation to generate at least one confidence level that the natural language output data generated using the natural language analysis operation contains error;

wherein the natural language analysis operation further comprises, based at least in part on the at least one confidence level that the natural language output data contains an error, selecting a portion of the disfluency natural language data stored in the memory and embedding the selected portion of the disfluency natural language data into the natural language output data;

wherein the selected portion of the disfluency natural language data is embedded into the natural language output data in a location selected to communicate that a portion of the natural language output data may contain an error; and

convert, using the natural language output module, the natural language output data that has been embedded with the selected portion of the disfluency natural language data into speech or text.

2. The SS system of claim 1, wherein:

the natural language input comprises a source language;

the natural language output comprises a target language; and

the natural language analysis comprises a natural language translation.

3. The SS system of claim 1, wherein:

the natural language input comprises a natural language question; and

the natural language output comprises a natural language answer.

4. A speech synthesizer (SS) system configured to convert natural language inputs to natural language outputs and provide a natural language alert that communicates that the natural language outputs may contain error, the SS system comprising:

a memory having disfluency natural language data stored therein; and

a processor-based input/output module system communicatively coupled to the memory;

wherein the input/output module comprises a natural language input module communicatively coupled to a machine translation module;

wherein the input/output module further comprises a natural language output module communicatively coupled to the machine translation module;

wherein the input/output module is configured to;

receive, using the natural language input module, a natural language input, wherein the natural language input comprises a source human language;

convert, using the natural language input module, the natural language input to natural language input data;

perform, using the machine translation module, a translation operation on the natural language input data to translate the natural language input data to natural language output data that represents a target human language;

wherein the translation operation comprises performing a confidence level analysis on at least one portion of the translation operation to generate at least one confidence level signal that represents a confidence level that the natural language output data that results from the natural language translation operation contains error;

wherein the translation operation further comprises, based at least in part on the at least one confidence level that the natural language output data contains an error, selecting a portion of the disfluency natural language data stored in the memory and embedding the selected portion of the disfluency natural language data into the natural language output data;

wherein the selected portion of the disfluency natural language data is embedded into the natural language output data in a location selected to communicate that a portion of the natural language output data may contain an error; and

convert, using the natural language output module, the natural language output data that has been embedded with the selected portion of the disfluency natural language data into speech or text comprising a natural language output having disfluency, wherein the natural language output is in the target human language and the disfluency is in the target human language.

5. The SS system of claim 4, wherein the input/output module is further configured to:

based at least in part on the confidence level, integrate at least one prosodic parameter into the natural language output data.

6. The SS system of claim 4, wherein the disfluency comprises a non-lexical utterance that is derived from the target human language and communicates a degree of confidence.

7. The SS system of claim 4, wherein the speech comprises a linguistic utterance in the target human language that communicates a degree of confidence in the at least one portion of the translation operation.

8. The SS system of claim 4, wherein:

the translation operation comprises applying first constraints on how the selected portion of the disfluency natural language data is embedded into the natural language output data.

9. The SS system of claim 8, wherein:

the first constraints comprise varying how the translation operation is performed.

10. A computer program product for performing speech synthesis (SS) operations configured to convert natural language inputs to natural language outputs and provide a natural language alert that communicates that the natural language outputs may contain error, the computer program product comprising:

a computer readable storage medium having program instructions embodied therewith, wherein the computer readable storage medium is not a transitory signal per se, the program instructions readable by a processor system to cause the processor system to control an input/output module of a SS circuit to perform a method comprising;

receiving, using a natural language input module of the input/output module, a natural language input comprising a source human language;

converting, using the natural language input module of the input/output module, the natural language input to natural language input data;

performing, using a machine translation module of the input/output module, a translation operation on the natural language input data to translate the natural language input data to a natural language output that represents a target human language;

wherein the translation operation comprises performing a confidence level analysis on at least one portion of the translation operation to generate at least one confidence level signal that represents a confidence level that the natural language output data that results from the natural language translation operation contains error;

wherein the translation operation further comprises, based at least in part on the at least one confidence level that the natural language output data contains an error, selecting a portion of disfluency natural language data stored in a memory and embedding the selected portion of the disfluency natural language data into the natural language output data;

wherein the selected portion of the disfluency natural language data is embedded into the natural language output data in a location selected to communicate that a portion of the natural language output data may contain an error; and

converting the natural language output data that has been embedded with the selected portion of the disfluency natural language data into speech or text comprising a natural language output having disfluency, wherein the natural language output is in the target human language and the disfluency is in the target human language.

11. The computer program product of claim 10, wherein the method further comprises:

based at least in part on the confidence level, integrating, using the input/output module, at least one prosodic parameter into the natural language output data.

12. The computer program product of claim 10, wherein the disfluency comprises a non-lexical utterance, which is derived from the target human language and communicates a degree of confidence.

13. The computer program product of claim 10, wherein the speech comprises a linguistic utterance in the target human language that communicates a degree of confidence.

14. The computer program product of claim 10, wherein:

the translation operation comprises applying first constraints on how the selected portion of the disfluency natural language data is integrated into the natural language output data.

15. The computer program product of claim 14, wherein:

the first constraints comprise varying how the translation operation is performed.

16. A speech synthesizer (SS) system configured to convert natural language inputs to natural language outputs and provide a natural language alert that communicates that the natural language outputs may contain error, the SS system comprising:

a memory having disfluency natural language data stored therein; and

a processor system communicatively coupled to the memory; and

an input/output module coupled to the memory and the processor system;

wherein the input/output module is configured to;

receive a natural language input comprising a natural language question;

convert the natural language input to natural language input data;

perform an analysis operation on data of a corpus to generate natural language output data that represents a natural language answer to the natural language question;

wherein the analysis operation comprises performing a confidence level analysis on at least one portion of the analysis operation to generate at least one confidence level signal that represents a confidence level that the natural language output data that results from the analysis operation contains error;

wherein the analysis operation further comprises, based at least in part on the at least one confidence level that the natural language output data contains an error, selecting a portion of disfluency natural language data stored in a memory and embedding the selected portion of the disfluency natural language data into the natural language output data;

wherein the selected portion of the disfluency natural language data is embedded into the natural language output data in a location selected to communicate that a portion of the natural language output data may contain an error; and

convert the natural language output data that has been embedded with the selected portion of the disfluency natural language data into speech or text that comprises a natural language answer with disfluency.

17. The SS system of claim 16, wherein:

the disfluency comprises a non-lexical or a linguistic utterance that communicates a degree of confidence.

18. The SS system of claim 16, wherein:

the analysis operation comprises applying first constraints on how the first selected portion of the disfluency data is integrated into the NL output data.

19. The SS system of claim 18, wherein:

the first constraints comprise varying how the analysis operation is performed.