Temporal based word segmentation

1. A method comprising:

determining, by a computing device, using a machine learning model, and based on a plurality of prior user inputs, one or more temporal thresholds;

after receiving, at an initial time, a first input of at least one first textual character, receiving, by a computing device, at a subsequent time, a second input of at least one second textual character;

determining, by the computing device and based on the at least one first textual character and the at least one second textual character, a first character sequence and a second character sequence, wherein the second character sequence includes a space character between the at least one first textual character and the at least one second textual character and the first character sequence does not include the space character between the at least one first textual character and the at least one second textual character;

determining, by the computing device, a first score associated with the first character sequence and a second score associated with the second character sequence, wherein the first score is based on at least one of a first language model score or a first spatial model score associated with the first character sequence and the second score is based on at least one of a second language model score or a second spatial model score associated with the first character sequence;

adjusting, by the computing device, using at least one of the one or more temporal thresholds, and based on an amount of time between the first input and the second input, the second score to determine a third score associated with the second character sequence;

determining, by the computing device and based on the first score and the third score, whether to output an indication of the first character sequence or an indication of the second character sequence; and

responsive to determining to output the indication of the second character sequence, outputting, by the computing device, for display, san indication of the second character sequence.

2. The method of claim 1 , further comprising:

updating, by the computing device and using the machine learning module, at least one of the one or more temporal thresholds based on the first input and the second input.

3. The method of claim 1 , wherein adjusting the second score comprises, responsive to determining that the amount of time between the first input and the second input is greater than the at least one of the one or more temporal thresholds, increasing, by the computing device, the second score to determine the third score.

4. The method of claim 1 , wherein:

receiving the first input comprises detecting, by the computing device, a first selection of one or more keys of a keyboard; and

receiving the second input comprises detecting, by the computing device, a second selection of the one or more keys of the keyboard.

5. The method of claim 4 , wherein the keyboard is a graphical keyboard or a physical keyboard.

6. The method of claim 1 , wherein:

receiving the first input comprises detecting, by the computing device, at a presence-sensitive input device, first handwritten input; and

receiving the second input comprises detecting, by the computing device, at the presence-sensitive input device, second handwritten input.

7. The method of claim 6 , further comprising:

determining, by the computing device, based on the first handwritten input, a first location of the presence-sensitive input device at which the first input of the at least one first textual character is received;

determining, by the computing device, based on the second handwritten input, a second location of the presence-sensitive input device at which the second input of the at least one second textual character is received; and

adjusting, by the computing device, based on a distance between the first location and the second location, the second score to determine the third score.

8. The method of claim 7 , wherein adjusting the second score comprises:

increasing, by the computing device, based on the distance, the second score in response to determining that the distance satisfies a distance threshold; and

decreasing, by the computing device, based on the distance, the second score in response to determining that the distance does not satisfy the distance threshold.

9. The method of claim 1 , further comprising:

responsive to determining to output the indication of the first character sequence:

refraining from outputting the indication of the second character sequence; and

outputting, by the computing device, for display, the indication of the first character sequence.

10. A computing device comprising:

a presence-sensitive display;

at least one processor; and

a storage device that stores at least one module executable by the at least one processor to:

determine, using a machine learning model, and based on a plurality of prior user inputs, one or more temporal thresholds;

after receiving, at an initial time, an indication of a first input detected by the presence-sensitive display of at least one first textual character, receive, at a subsequent time, a second input detected by the presence-sensitive display of at least one second textual character;

determine, based on the at least one first textual character and the at least one second textual character, a first character sequence and a second character sequence, wherein the second character sequence includes a space character between the at least one first textual character and the at least one second textual character and the first character sequence does not include the space character between the at least one first textual character and the at least one second textual character;

determine a first score associated with the first character sequence and a second score associated with the second character sequence, wherein the first score is based on at least one of a first language model score or a first spatial model score associated with the first character sequence and the second score is based on at least one of a second language model score or a second spatial model score associated with the first character sequence;

adjust, using at least one of the one or more temporal thresholds, and based on an amount of time between the first input and the second input, the second score to determine a third score associated with the second character sequence;

determine, based on the first score and the third score, whether to output an indication of the first character sequence or an indication of the second character sequence; and

responsive to determining to output the indication of the second character sequence, output, for display by the presence-sensitive display, an indication of the second character sequence.

11. The computing device of claim 10 , wherein the at least one module is further executable by the at least one processor to update, using the machine learning module, at least one of the one or more temporal thresholds based on the first input and the second input.

12. The computing device of claim 10 , wherein the at least one module is further executable by the at least one processor to adjust the second scored by being executable by the at least one processor to, responsive to determining that the amount of time between the first input and the second input is greater than the at least one of the one or more temporal thresholds, increase the second score to determine the third score.

13. The computing device of claim 10 , wherein:

the first input comprises first handwritten input; and

the second input comprises second handwritten input.

14. The computing device of claim 13 , wherein the at least one module is further executable by the at least one processor to adjust the second score by at least being executable to:

determine, based on the first handwritten input, a first location of the presence-sensitive input device at which the first input of the at least one first textual character is received;

determine, based on the second handwritten input, a second location of the presence-sensitive input device at which the second input of the at least one second textual character is received; and

adjust, based on a distance between the first location and the second location, the second score to determine the third score.

15. The computing device of claim 14 , wherein the at least one module is further executable by the at least one processor to adjust the second score by at least being executable to:

increase, based on the distance, the second score in response to determining that the distance satisfies a distance threshold; and

decrease, based on the distance, the second score in response to determining that the distance does not satisfy the distance threshold.

16. A computer-readable storage medium comprising instructions that, when executed by at least one processor of a computing device, cause the at least one processor to:

determine, using a machine learning model, and based on a plurality of prior user inputs, one or more temporal thresholds;

after receiving, at an initial time, a first input of at least one first textual character, receive, at a subsequent time, a second input of at least one second textual character;

determine, based on the at least one first textual character and the at least one second textual character, a first character sequence and a second character sequence, wherein the second character sequence includes a space character between the at least one first textual character and the at least one second textual character and the first character sequence does not include the space character between the at least one first textual character and the at least one second textual character;

determine a first score associated with the first character sequence and a second score associated with the second character sequence, wherein the first score is based on at least one of a first language model score or a first spatial model score associated with the first character sequence and the second score is based on at least one of a second language model score or a second spatial model score associated with the first character sequence;

adjust, using at least one of the one or more temporal thresholds, and based on an amount of time between the first input and the second input, the second score to determine a third score associated with the second character sequence;

determine, based on the first score and the third score, whether to output an indication of the first character sequence or an indication of the second character sequence; and

responsive to determining to output the indication of the second character sequence, output, for display, an indication of the second character sequence.

17. The computer-readable storage medium of claim 16 comprising additional instructions that, when executed by the at least one processor of the computing device, cause the at least one processor to update, using the machine learning module, at least one of the one or more temporal thresholds based on the first input and the second input.

18. The computer-readable storage medium of claim 16 , wherein the instructions that cause the at least one processor to adjust the second score comprise instructions that cause the at least one processor to, responsive to determining that the amount of time between the first input and the second input is greater than the at least one of the one or more temporal thresholds, increase the second score to determine the third score.

19. The computer-readable storage medium of claim 16 , wherein:

the first input is a selection of a first one or more keys of a keyboard;

the second input is a selection of a second one or more keys of the keyboard; and

the keyboard is a graphical keyboard or a physical keyboard.

20. The computer-readable storage medium of claim 16 , wherein:

the first input comprises first handwritten input;

the second input comprises second handwritten input; and

the at least one module is further executable by the at least one processor to adjust the second score by at least being executable to:

determine, based on the first handwritten input, a first location of the presence-sensitive input device at which the first input of the at least one first textual character is received;

determine, based on the second handwritten input, a second location of the presence-sensitive input device at which the second input of the at least one second textual character is received; and

adjust, based on a distance between the first location and the second location, the second score to determine the third score.