Expandable dialogue system
A method for training a dialogue learning model includes presenting, via a user interface of a computing device, an utterance and a list of actions based on the utterance. A selection of an action from the list of actions is received via the user interface. A designated span of the utterance is received via the user interface. The selected action and the designated span of the utterance is provided to a computing system for training the dialogue learning model.
1. A method for training a dialogue learning model, comprising:
presenting, via a user interface of a computing device, an utterance and a list of actions based on the utterance;
receiving, via the user interface of the computing device, a selection of an action from the list of actions;
receiving, via the user interface of the computing device, a designated span of the utterance;
training the dialogue learning model based on the selected action and the designated span of the utterance to recognize an association between the selected action and natural language content in the designated span of the utterance; and
generating one or more rules based on the association between the selected action and the natural language content.
2. The method of claim 1 , wherein the list of actions includes two or more actions.
3. The method of claim 1 , wherein the designated span of the utterance is less than an entirety of the utterance.
4. The method of claim 1 , wherein the utterance is a user utterance from a natural language conversation between a user and an automated assistant.
5. The method of claim 1 , wherein the selected action is one of a plurality of actions for responding to the utterance, and the designated span of the utterance is one of a plurality of designated spans of the utterance each corresponding to an action of the plurality of actions.
6. The method of claim 1 , wherein the natural language content includes one or more tokens within the utterance.
7. The method of claim 1 , wherein the one or more rules include a rule for recognizing whether the selected action is applicable based on the natural language content.
8. The method of claim 1 , wherein the one or more rules include a rule for determining parameters of the selected action based on the natural language content.
9. The method of claim 1 , wherein the one or more rules include a rule for generating an agent utterance describing the selected action.
10. The method of claim 1 , wherein the dialogue learning model is a grammar induction learning model and the one or more rules are grammar rules derived based on the association by the grammar induction learning model.
11. The method of claim 1 , wherein each of the one or more rules is associated with a set of features, and the training of the dialogue learning model includes assessing relevance of one or more features in the set of features, based on the association.
12. A method for training a dialogue learning model, comprising:
receiving, from a computing device including a user interface, an utterance and a list of actions based on the utterance as presented via the user interface;
receiving, from the computing device including the user interface, a selection of an action from the list of actions as selected via the user interface;
receiving, from the computing device including the user interface, a designated span of the utterance as selected via the user interface;
training the dialogue learning model with the selected action and the designated span of the utterance to recognize an association between the selected action and the designated span of the utterance; and
generating one or more rules based on the association.
13. The method of claim 12 , wherein the list of actions includes two or more actions.
14. The method of claim 12 , wherein the designated span of the utterance is less than an entirety of the utterance.
15. A computer system, comprising:
a processor; and
a storage device holding instructions executable by the processor to:
receive, at a computing device, a selection of an action from a list of actions based on an utterance;
automatically train a dialogue learning model with the action and a designated span of the utterance less than an entirety of the utterance to recognize an association between the selected action and natural language content in the designated span of the utterance; and
generating one or more rules based on the association between the selected action and the natural language content.
16. The computer system of claim 15 , wherein the list of actions includes two or more actions.
17. The computer system of claim 15 , wherein the utterance is a user utterance received via a user interface.
18. The computer system of claim 15 , wherein the action is one of a plurality of actions for responding to the utterance, and the designated span of the utterance is one of a plurality of designated spans of the utterance each corresponding to an action of the plurality of actions.