Developer platform for providing automated assistant in new domains
A system that provides a sharable language interface for implementing automated assistants in new domains and applications. A dialogue assistant that is trained in a first domain can receive a specification in a second domain. The specification can include language structure data such as schemas, recognizers, resolvers, constraints and invariants, actions, language hints, generation template, and other data. The specification data is applied to the automated assistant to enable the automated assistant to provide interactive dialogue with a user in a second domain associated with the received specification. In some instances, portions of the specification may be automatically mapped to portions of the first domain. By having the ability to learn new domains and applications through receipt of objects and properties rather than retooling the interface entirely, the present system is much more efficient at learning how to provide interactive dialogue in new domains than previous systems.
1. A method for providing an automated assistant in multiple domains, comprising:
receiving a domain-specific specification including a description of a constraint for the automated assistant, the automated assistant previously trained with training data for a first domain different than a second domain corresponding to the domain-specific specification;
using a previously-trained semantic parser to map the description of the constraint to a constraint template; and
enabling the automated assistant to conduct interactive dialogue in the second domain without training data specific to the second domain, based on the constraint template and general features derived from the previous training with the training data for the first domain and domain-specific features for the second domain indicated in the domain-specific specification.
2. The method of claim 1 , wherein the automated assistant automatically maps corresponding specification elements to corresponding elements associated with the first domain.
3. The method of claim 1 , wherein the domain-specific specification includes objects and properties of objects that are true within the second domain.
4. The method of claim 1 , wherein the domain-specific specification includes schema that includes properties.
5. The method of claim 1 , wherein the domain-specific specification includes a recognizer that identifies entities in language.
6. The method of claim 1 , wherein the domain-specific specification includes a resolver that converts a system query language into a call.
7. The method of claim 1 , wherein the domain-specific specification includes a language hint.
8. The method of claim 1 , wherein the domain-specific specification includes a generation template.
9. A computer readable storage device having embodied thereon a program, the program being executable by a processor to perform a method for providing an automated assistant in multiple domains, the method comprising:
receiving a domain-specific specification including a description of a constraint for the automated assistant, the automated assistant previously trained with training data for a first domain different than a second domain corresponding to the domain-specific specification;
using a previously-trained semantic parser to map the description of the constraint to a constraint template; and
enabling the automated assistant to conduct interactive dialogue in the second domain without training data specific to the second domain, based on the constraint template and general features derived from the previous training with the training data for the first domain and domain-specific features for the second domain indicated in the domain-specific specification.
10. The computer readable storage device of claim 9 , wherein the automated assistant automatically maps corresponding specification elements to corresponding elements associated with the first domain.
11. The computer readable storage device of claim 9 , wherein the domain-specific specification includes objects and properties of objects that are true within the second domain.
12. The computer readable storage device of claim 9 , wherein the domain-specific specification includes schema that includes properties.
13. The computer readable storage device of claim 9 , wherein the domain-specific specification includes a recognizer that identifies entities in language.
14. The computer readable storage device of claim 9 , wherein the domain-specific specification includes a resolver that converts a system query language into a call.
15. The computer readable storage device of claim 9 , wherein the domain-specific specification includes a language hint.
16. The computer readable storage device of claim 9 , wherein the domain-specific specification includes a generation template.
17. The method of claim 1 , wherein the description of the constraint is a natural language description.
18. The method of claim 1 , wherein the constraint is a violable constraint having differing degrees of violation.
19. The method of claim 18 , wherein the differing degrees of violation have differing associated costs.
20. A method for providing an automated assistant in multiple domains, comprising:
training the automated assistant for a first domain with first-domain training data;
receiving a second-domain-specific specification for a second domain different than the first domain, the second-domain-specific specification including a description of a constraint for the second domain;
using a previously-trained semantic parser to map the description of the constraint for the second domain to a constraint template for the second domain, the constraint template for the second domain configured for training the automated assistant for the second domain without training data specific to the second domain; and
expanding the automated assistant to conduct dialogue in the second domain based on general features derived from previous training with the first-domain training data and the constraint template for the second domain.