COMPUTER-IMPLEMENTED METHOD FOR AUTOMATIC TRAINING OF A DIALOGUE SYSTEM, AND DIALOGUE SYSTEM FOR GENERATING SEMANTIC ANNOTATIONS

• US 20140324429A1
• Filed: 04/24/2014
• Published: 10/30/2014
• Est. Priority Date: 04/25/2013
• Status: Active Grant

• Current Assignee: Elektrobit Automotive GmbH (Continental AG)
• Original Assignee: Elektrobit Automotive GmbH (Continental AG)
• Inventors: Weilhammer, Karl, Goronzy-Thomae, Silke
• Granted Patent: US 9,679,557 B2
• Time in Patent Office: Days
• US Class Current: 704/244
• CPC Class Codes: G10L 15/063 Training
• CPC Class Codes: G10L 15/1815 Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding

Abstract

An adaptive dialogue system and also a computer-implemented method for semantic training of a dialogue system are disclosed. In this connection, semantic annotations are generated automatically on the basis of received speech inputs, the semantic annotations being intended for controlling instruments or for communication with a user. For this purpose, at least one speech input is received in the course of an interaction with a user. A sense content of the speech input is registered and appraised, by the speech input being classified on the basis of a trainable semantic model, in order to make a semantic annotation available for the speech input. Further user information connected with the speech input is taken into account if the registered sense content is appraised erroneously, incompletely and/or as untrustworthy. The sense content of the speech input is learned automatically on the basis of the additional user information.

Claims

1. A computer-implemented method for automatic training of a dialogue system, in order to generate semantic annotations automatically on the basis of a received speech input, the semantic annotations being intended for controlling instruments or for communication with a user, the method comprising the following steps:

receiving at least one speech input in the course of an interaction with a user;

registering and appraising a sense content of the speech input, by the speech input being classified on the basis of a trainable semantic model, in order to make a semantic annotation available automatically for the speech input;

taking into account further user information connected with the reception of the speech input if the registered sense content is appraised erroneously, incompletely and/or as untrustworthy; and

automatic learning of the sense content of the speech input on the basis of the additional user information.

2. The method according to claim 1, further including:

training the semantic model on the basis of at least one of the received speech input, the learned sense content of the speech input and a corresponding transcription into a semantic annotation.

3. The method according to claim 1, wherein the learning step is undertaken on the basis of the user information only when a connection between the reception of the speech input and the user information can be established.

4. The method according to claim 3, wherein the connection between the reception of the speech input and the user information is determined on the basis of at least one of a temporal and semantic correlation.

5. The method according to claim 1, wherein the learning step includes at least one of the following steps:

establishing the sense content of the user information;

comparing the received speech input with the sense content of the user information; and

successively deriving or completing the sense content of the received speech input on the basis of a known sense content of the user information.

6. The method according to claim 1, wherein the taking of further user information into account and the learning are continued until such time as the sense content of the received speech input is recognised completely and/or as trustworthy or is terminated by a user-abort action.

7. The method according to claim 1, wherein the trustworthiness of the sense content of the speech input is assessed on the basis of confidence values allocated in the course of the classification of the speech input.

8. The method according to claim 1, wherein the learning includes at least one of the following procedures:

completing an incompletely classified received speech input;

correcting a misinterpreted part of the received speech input; and

reclassifying an incorrectly classified or non-classified speech input.

9. The method according to claim 1, wherein the step of taking the user information into account includes deriving the user information from at least one user input that immediately follows the reception of the speech input.

10. The method according to claim 9, wherein the at least one user input includes at least one correcting control input which corrects a preceding control command made available on the basis of the speech input.

11. The method according to claim 1, wherein the step of taking the user information into account further includes at least one of the following steps:

making a restricted number of input options available; and

receiving one or more user inputs on the basis of the input options made available.

12. The method according to claim 9, wherein the user inputs are based on acoustic or haptic actions of the user.

13. A computer-program product with program code for carrying out the process according to at least one of the preceding claims when the computer-program product is executed on a computer device.

14. The computer-program product according to claim 13, which has been stored on a computer-readable recording medium.

15. An adaptive dialogue system for use in terminals, which has been designed to generate semantic annotations automatically on the basis of received speech inputs, the semantic annotations being intended for controlling the terminals or for communication with a user, comprising:

an input interface which is designed to receive at least one speech input in the course of an interaction with a user;

a semantic classifying device which is designed to register and classify the sense content of the speech input on the basis of a trainable semantic model, to make a semantic annotation available automatically for the speech input on the basis of the classification, to take into account further user information connected with the reception of the speech input if the registered sense content is appraised erroneously, incompletely and/or as untrustworthy, and to learn the sense content of the speech input on the basis of the additional user information.

16. The adaptive dialogue system according to claim 15, further including a training device which is provided to train the semantic model on the basis of at least one of the learned sense content of a speech input, the speech input, and a transcription into a semantic annotation.

17. The adaptive dialogue system according to claim 15, further including a storage device which is provided to store, entirely or partly, at least one of the received speech input, the learned sense content of the received speech input and a transcription into a semantic annotation.

18. The adaptive dialogue system according to claim 15, further including a dialogue manager which is provided to make an input prompt available to a user in order to obtain additional information if a classification result has been appraised erroneously, incompletely or as untrustworthy.

19. The adaptive dialogue system according to claim 15, wherein the semantic model has been designed in the form of a neural network or a decision tree.

20. The adaptive dialogue system according to claim 15, further including a communications device which is provided to send to a server or to retrieve from a server the received speech input together with at least one of the learned sense content of the speech input and with the transcription.

21. The adaptive dialogue system according to claim 15, wherein the adaptive dialogue system is part of a human/machine interface.

22. A control device for a vehicle, including the dialogue system according to claim 15.