Assistive browsing using context

1. A system comprising:

one or more user devices, and

one or more computers and one or more storage devices on which are stored instructions that are operable when executed to cause the one or more user devices and the one or more computers to perform operations, comprising:

maintaining a search index of resources, wherein each resource comprises respective content at a respective location identified by a respective resource address;

receiving, through a first user device of the one or more user devices, a spoken first query from a user;

providing, to the user and through the first user device, first content of a first resource as a spoken first response to the spoken first query;

obtaining context data, wherein the context data is the first content of the first resource and the context data comprises third terms, the third terms comprising a noun;

receiving, through the first user device, a spoken second query from the user following the providing of the spoken first response, the spoken second query comprising second terms, the second terms comprising a pronoun;

generating a revised query from the spoken second query using the context data, comprising replacing at least one of the second terms with at least one of the third terms, comprising replacing the pronoun with the noun;

identifying, using the revised query, one or more resources indexed according to the search index of resources, wherein the one or more resources are each responsive to the revised query, and wherein the one or more resources comprise a second resource having second content; and

providing, to the user through the first user device, the second content of the second resource as a spoken second response to the spoken second query.

2. The system of claim 1 , wherein generating the revised query from the spoken second query using the context data further comprises:

providing the spoken second query and the context data to a query revision engine; and

receiving the revised query from the query revision engine.

3. The system of claim 1 ,

wherein generating the revised query from the spoken second query using the context data further comprises modifying at least one of the second terms of the spoken second query using the context data.

4. The system of claim 1 ,

wherein generating the revised query from the spoken second query using the context data further comprises adding at least one of the third terms to the second terms.

5. The system of claim 1 , wherein the operations further comprise determining that the spoken second query is a contextual query based on one or more terms in the spoken second query, and

wherein generating the revised query from the spoken second query using the context data further comprises generating the revised query from the spoken second query using the context data and in response to determining that the spoken second query is a contextual query.

6. The system of claim 1 , wherein the operations further comprise selecting the second resource from the one or more resources, comprising:

ranking the one or more resources using the context data; and

selecting the second resource based on the ranking.

7. The system of claim 1 ,

wherein the second content comprises text, and

wherein providing, to the user through the first user device, the second content of the second resource as the spoken second response to the spoken second query comprises speaking the text of the second content.

8. The system of claim 1 , wherein the operations further comprise displaying, through the first user device and in response to the spoken second query, the second resource on a display of the first user device.

9. The system of claim 8 , wherein displaying, through the first user device and in response to the spoken second query, the second resource on the display of the first user device comprises providing instructions to cause a web browser on the first user device to open a tab and display the second resource in the tab.

10. A method, comprising:

maintaining a search index of resources, wherein each resource comprises respective content at a respective location identified by a respective resource address;

receiving, through a first user device of one or more user devices, a spoken first query from a user;

providing, to the user and through the first user device, first content of a first resource as a spoken first response to the spoken first query;

obtaining context data, wherein the context data is the first content of the first resource and the context data comprises third terms, the third terms comprising a noun;

receiving, through the first user device, a spoken second query from the user following the providing of the spoken first response, the spoken second query comprising second terms, the second terms comprising a pronoun;

generating a revised query from the spoken second query using the context data, comprising replacing at least one of the second terms with at least one of the third terms, comprising replacing the pronoun with the noun;

identifying, using the revised query, one or more resources indexed according to the search index of resources, wherein the one or more resources are each responsive to the revised query, and wherein the one or more resources comprise a second resource having second content; and

providing, to the user through the first user device, the second content of the second resource as a spoken second response to the spoken second query.

11. The method of claim 10 , wherein generating the revised query from the spoken second query using the context data further comprises:

providing the spoken second query and the context data to a query revision engine; and

receiving the revised query from the query revision engine.

12. The method of claim 10 ,

wherein generating the revised query from the spoken second query using the context data further comprises modifying at least one of the second terms of the spoken second query using the context data.

13. The method of claim 10 ,

wherein generating the revised query from the spoken second query using the context data further comprises adding at least one of the third terms to the second terms.

14. The method of claim 10 , further comprising determining that the spoken second query is a contextual query based on one or more terms in the spoken second query, and

wherein generating the revised query from the spoken second query using the context data further comprises generating the revised query from the spoken second query using the context data and in response to determining that the spoken second query is a contextual query.

15. The method of claim 10 , comprising selecting the second resource from the one or more resources, comprising:

ranking the one or more resources using the context data; and

selecting the second resource based on the ranking.

16. The method of claim 10 ,

wherein the second content comprises text, and

wherein providing, to the user through the first user device, the second content of the second resource as the spoken second response to the spoken second query comprises speaking the text of the second content.

17. The method of claim 10 , further comprising displaying, through the first user device and in response to the spoken second query, the second resource on a display of the first user device.

18. The method of claim 17 , wherein displaying, through the first user device and in response to the spoken second query, the second resource on the display of the first user device comprises providing instructions to cause a web browser on the first user device to open a tab and display the second resource in the tab.

19. One or more non-transitory computer-readable storage media encoded with instructions that, when executed by one or more computers and one or more user devices, cause the one or more computers and the one or more user devices to perform operations comprising:

maintaining a search index of resources, wherein each resource comprises respective content at a respective location identified by a respective resource address;

receiving, through a first user device of the one or more user devices, a spoken first query from a user;

providing, to the user and through the first user device, first content of a first resource as a spoken first response to the spoken first query;

obtaining context data, wherein the context data is the first content of the first resource and the context data comprises third terms, the third terms comprising a noun;

receiving, through the first user device, a spoken second query from the user following the providing of the spoken first response, the spoken second query comprising second terms, the second terms comprising a pronoun;

generating a revised query from the spoken second query using the context data, comprising replacing at least one of the second terms with at least one of the third terms, comprising replacing the pronoun with the noun;

identifying, using the revised query, one or more resources indexed according to the search index of resources, wherein the one or more resources are each responsive to the revised query, and wherein the one or more resources comprise a second resource having second content; and

providing, to the user through the first user device, the second content of the second resource as a spoken second response to the spoken second query.

20. The computer-readable storage media of claim 19 , wherein generating the revised query from the spoken second query using the context data further comprises:

providing the spoken second query and the context data to a query revision engine; and

receiving the revised query from the query revision engine.

21. The computer-readable storage media of claim 19 ,

wherein generating the revised query from the spoken second query using the context data further comprises modifying at least one of the second terms of the spoken second query using the context data.

22. The computer-readable storage media of claim 19 ,

wherein generating the revised query from the spoken second query using the context data further comprises adding at least one of the third terms to the second terms.

23. The computer-readable storage media of claim 19 , wherein the operations further comprise determining that the spoken second query is a contextual query based on one or more terms in the spoken second query, and

wherein generating the revised query from the spoken second query using the context data further comprises generating the revised query from the spoken second query using the context data and in response to determining that the spoken second query is a contextual query.

24. The computer-readable storage media of claim 19 , wherein the operations further comprise selecting the second resource from the one or more resources, comprising:

ranking the one or more resources using the context data; and

selecting the second resource based on the ranking.

25. The computer-readable storage media of claim 19 ,

wherein the second content comprises text, and

wherein providing, to the user through the first user device, the second content of the second resource as the spoken second response to the spoken second query comprises speaking the text of the second content.

26. The computer-readable storage media of claim 19 , wherein the operations further comprise displaying, through the first user device and in response to the spoken second query, the second resource on a display of the first user device.

27. The computer-readable storage media of claim 26 , wherein displaying, through the first user device and in response to the spoken second query, the second resource on the display of the first user device comprises providing instructions to cause a web browser on the first user device to open a tab and display the second resource in the tab.