Multi-gesture text input prediction

1. A method comprising:

displaying, by a computing device, a graphical keyboard comprising a plurality of alphabet character keys and a terminating key, the terminating key comprising a portion of the graphical keyboard that is not indicative of the alphabet character keys;

receiving, by the computing device, data for one or more first gestures that indicate selection of a first set of alphabet character keys from the plurality of alphabet character keys, the data for the one or more first gestures not indicating selection of the terminating key;

prior to the computing device receiving a completion of data for the one or more first gestures, determining, by the computing device and based on the first set of alphabet character keys, a first candidate string, the first candidate string including multiple first candidate words separated by one or more space characters;

displaying, by the computing device, the first candidate string;

determining whether the computing device has not completed receiving the data for the one or more first gestures that do not indicate selection of the terminating key;

responsive to determining that the computing device has not completed receiving the data for the one or more first gestures:

incrementally processing, by the computing device, additional data for the one or more first gestures, the additional data indicating selection of additional alphabet character keys from the plurality of alphabet character keys;

determining, by the computing device, whether the additional alphabet character keys associated with the additional data are included or not included in the first candidate string; and

responsive to determining that the additional alphabet character keys are included in the first candidate string, continuing, by the computing device, to display the first candidate string; or

responsive to determining that the additional alphabet character keys are not included in the first candidate string:

determining, by the computing device, a replacement candidate string that includes the first set of alphabet character keys and the additional alphabet character keys, the replacement candidate string including multiple replacement candidate words separated by one or more space characters; and

displaying, by the computing device, the replacement candidate string.

2. The method of claim 1 , the method further comprising outputting, by the computing device and for display, one or more auto-completion suggestions overlaid on the graphical keyboard, wherein the one or more auto-completion suggestions are based at least in part on the first candidate string or the replacement candidate string.

3. The method of claim 2 , the method further comprising:

receiving, by the computing device, an indication of a second gesture to select an auto-completion suggestion from the one or more auto-completion suggestions; and

outputting, by the computing device and for display, a hard-commit word, wherein the hard-commit word is based at least in part on the selected auto-completion suggestion.

4. The method of claim 1 , wherein determining whether the additional alphabet character keys associated with the additional data are included or not included in the first candidate string comprises:

determining, by the computing device, a second candidate string in which the additional alphabet character keys associated with the additional data are included in the first candidate string;

determining, by the computing device, a third candidate string in which the additional alphabet character keys associated with the additional data are included in the replacement candidate string; and

comparing, by the computing device, a first cost value associated with the second candidate string and a second cost value associated with the replacement candidate string, wherein the first and second cost values are determined based at least in part on a lexicon.

5. The method of claim 1 , wherein displaying the first candidate string or the replacement candidate string comprises outputting, by the computing device and for display, at least one suggestion region, wherein:

the multiple first candidate words of the first candidate string are output in the suggestion region; and

the multiple replacement candidate words of the replacement candidate string are output in the suggestion region.

6. The method of claim 1 , wherein the one or more first gestures are tap gestures.

7. The method of claim 1 , wherein the one or more first gestures is a continuous gesture.

8. The method of claim 1 , wherein the terminating key is a spacebar key of the graphical keyboard.

9. A non-transitory computer-readable storage medium encoded with instructions that, when executed, cause one or more processors of a computing device to:

display a graphical keyboard comprising a plurality of alphabet character keys and a terminating key, the terminating key comprising a portion of the graphical keyboard that is not indicative of the alphabet character keys;

receive data for one or more first gestures that indicate selection of a first set of alphabet character keys from the plurality of alphabet character keys, the data for the one or more first gestures not indicating selection of the terminating key;

prior to a reception of a completion of data for the one or more first gestures, determine, based on the first set of alphabet character keys, a first candidate string, the first candidate string including multiple first candidate words separated by one or more space characters;

display the first candidate string;

determine whether the computing device has not completed receiving the data for the one or more first gestures that do not indicate selection of the terminating key;

responsive to a determination that the computing device has not completed receiving the data for the one or more first gestures:

incrementally process additional data for the one or more first gestures, the additional data indicating selection of additional alphabet character keys from the plurality of alphabet character keys;

determine whether the additional alphabet character keys associated with the additional data are included or not included in the first candidate string; and

responsive to a determination that the additional alphabet character keys are included in the first candidate string, continue to display the first candidate string; or

responsive to a determination that the additional alphabet character keys are not included in the first candidate string:

determine a replacement candidate string that includes the first set of alphabet character keys and the additional alphabet character keys, the replacement candidate string including multiple replacement candidate words separated by one or more space characters; and

display the replacement candidate string.

10. The non-transitory computer-readable storage medium of claim 9 , wherein the instructions, when executed, further cause the one or more processors to:

output for display one or more auto-completion suggestions overlaid on the graphical keyboard, wherein the one or more auto-completion suggestions are based at least in part on the first candidate string or the replacement candidate string.

11. The non-transitory computer-readable storage medium of claim 10 , wherein the instructions, when executed, further cause the one or more processors to:

receive an indication of a second gesture to select an auto-completion suggestion from the one or more auto-completion suggestions; and

output for display a hard-commit word, wherein the hard-commit word is based at least in part on the selected auto-completion suggestion.

12. The non-transitory computer-readable storage medium of claim 9 , wherein a determination whether the additional alphabet character keys associated with the additional data are included or not included in the first candidate string comprises:

determine a second candidate string in which the additional alphabet character keys associated with the additional data are included in the first candidate string;

determine a third candidate string in which the additional alphabet character keys associated with the additional data are included in the replacement candidate string; and

compare a first cost value associated with the second candidate string and a second cost value associated with the replacement candidate string, wherein the first and second cost values are determined based at least in part on a lexicon.

13. The non-transitory computer-readable storage medium of claim 9 , wherein the display of the first candidate string or the replacement candidate string comprises output for display at least one suggestion region, wherein:

the multiple first candidate words of the first candidate string are output in the suggestion region; and

the multiple replacement candidate words of the replacement candidate string are output in the suggestion region.

14. The non-transitory computer-readable storage medium of claim 9 , wherein the one or more first gestures are tap gestures.

15. The non-transitory computer-readable storage medium of claim 9 , wherein the one or more first gestures is a continuous gesture.

16. The non-transitory computer-readable storage medium of claim 9 , wherein the terminating key is a spacebar key of the graphical keyboard.

17. A computing device, comprising one or more processors configured to:

display a graphical keyboard comprising a plurality of alphabet character keys and a terminating key, the terminating key comprising a portion of the graphical keyboard that is not indicative of the alphabet character keys;

receive data for one or more first gestures that indicate selection of a first set of alphabet character keys from the plurality of alphabet character keys, the data for the one or more first gestures not indicating selection of the terminating key;

prior to a reception of a completion of data for the one or more first gestures, determine, based on the first set of alphabet character keys, a first candidate string, the first candidate string including multiple first candidate words separated by one or more space characters;

display the first candidate string;

determine whether the computing device has not completed receiving the data for the one or more first gestures that do not indicate selection of the terminating key;

responsive to a determination that the computing device has not completed receiving the data for the one or more first gestures:

incrementally process additional data for the one or more first gestures, the additional data indicating selection of additional alphabet character keys from the plurality of alphabet character keys;

determine whether the additional alphabet character keys associated with the additional data are included or not included in the first candidate string; and

responsive to a determination that the additional alphabet character keys are included in the first candidate string, continue to display the first candidate string; or

responsive to a determination that the additional alphabet character keys are not included in the first candidate string:

determine a replacement candidate string that includes the first set of alphabet character keys and the additional alphabet character keys, the replacement candidate string including multiple replacement candidate words separated by one or more space characters; and

display the replacement candidate string.

18. The computing device of claim 17 , wherein the one or more processors are further configured to:

output for display one or more auto-completion suggestions overlaid on the graphical keyboard, wherein the one or more auto-completion suggestions are based at least in part on the first candidate string or the replacement candidate string.

19. The computing device of claim 18 , wherein the one or more processors are further configured to:

receive an indication of a second gesture to select an auto-completion suggestion from the one or more auto-completion suggestions; and

output for display a hard-commit word, wherein the hard-commit word is based at least in part on the selected auto-completion suggestion.

20. The computing device of claim 17 , wherein the display of the first candidate string or the replacement candidate string comprises output for display at least one suggestion region, wherein:

the multiple first candidate words of the first candidate string are output in the suggestion region; and

the multiple replacement candidate words of the replacement candidate string are output in the suggestion region.