Dialog session override policies for assistant systems

1. A method comprising, by a client system:

receiving, at the client system, a user input, wherein the user input is associated with one or more intents and one or more slots;

generating one or more first dialog acts based on the user input;

calculating a task-confidence score based on one or more intent-confidence scores associated with the one or more intents, respectively, and one or more slot-confidence scores associated with the one or more slots, respectively;

generating, responsive to the task-confidence score being less than a threshold score, one or more second dialog acts modifying the one or more first dialog acts; and

presenting, at the client system, a response to the user input, wherein the response is based on one or more of the first dialog acts or the second dialog acts.

2. The method of claim 1 , further comprising:

determining a task based on the user input, wherein the task is associated with the one or more intents and the one or more slots.

3. The method of claim 2 , wherein generating the one or more first dialog acts is further based on a task policy, wherein the task policy specifies dialog acts associated with the task.

4. The method of claim 3 , wherein generating the one or more second dialog acts further comprises:

analyzing the task policy and the one or more first dialog acts by one or more rules.

5. The method of claim 3 , wherein generating the one or more second dialog acts further comprises:

analyzing the task policy and the one or more first dialog acts by one or more machine-learning models, wherein the machine-learning models comprise one or more of a sequence-to-sequence model, a variational auto-encoder, a deep recurrent and convolutional neural network, or a generate-and-rank model.

6. The method of claim 1 , wherein the user input is associated with a user, the method further comprising:

accessing a current dialog state associated with the user; and

updating the current dialog state based on the user input and contextual information associated with the user input.

7. The method of claim 6 , wherein generating the one or more first dialog acts is further based on the updated dialog state associated with the user.

8. The method of claim 1 , wherein one or more of the second dialog acts are associated with augmentations to one or more of the first dialog acts.

9. The method of claim 1 , wherein one or more of the second dialog acts are associated with replacements of one or more of the first dialog acts.

10. The method of claim 1 , wherein one or more of the second dialog acts are associated with one or more confirmation requests.

11. The method of claim 1 , wherein one or more of the second dialog acts are associated with terminations of one or more of the first dialog acts.

12. The method of claim 1 , wherein one or more of the second dialog acts are associated with a change of a modality for presenting the response.

13. The method of claim 1 , wherein one or more of the second dialog acts are associated with a change of a user interface for presenting the response.

14. The method of claim 1 , wherein one or more of the second dialog acts are associated with error-corrections of one or more of the first dialog acts.

15. The method of claim 1 , wherein generating the one or more first dialog acts comprises providing the user input to a third-party agent via an application programming interface (API), and wherein the one or more first dialog acts are generated based on an execution of a task based on the user input by the third-party agent.

16. One or more computer-readable non-transitory storage media embodying software that is operable when executed to:

receive, at a client system, a user input, wherein the user input is associated with one or more intents and one or more slots;

generate one or more first dialog acts based on the user input;

calculate a task-confidence score based on one or more intent-confidence scores associated with the one or more intents, respectively, and one or more slot-confidence scores associated with the one or more slots, respectively;

generate, responsive to the task-confidence score being less than a threshold score, one or more second dialog acts modifying the one or more first dialog acts; and

present, at the client system, a response to the user input, wherein the response is based on one or more of the first dialog acts or the second dialog acts.

17. The media of claim 16 , wherein one or more of the second dialog acts are associated with augmentations to one or more of the first dialog acts.

18. The media of claim 16 , wherein one or more of the second dialog acts are associated with replacements of one or more of the first dialog acts.

19. The media of claim 16 , wherein one or more of the second dialog acts are associated with one or more confirmation requests.

20. A system comprising: one or more processors; and a non-transitory memory coupled to the processors comprising instructions executable by the processors, the processors operable when executing the instructions to:

receive, at a client system, a user input, wherein the user input is associated with one or more intents and one or more slots;

generate one or more first dialog acts based on the user input;

calculate a task-confidence score based on one or more intent-confidence scores associated with the one or more intents, respectively, and one or more slot-confidence scores associated with the one or more slots, respectively;

generate, responsive to the task-confidence score being less than a threshold score, one or more second dialog acts modifying the one or more first dialog acts; and

present, at the client system, a response to the user input, wherein the response is based on one or more of the first dialog acts or the second dialog acts.