Selection biasing
In some implementations, data indicating a touch received on a proximity-sensitive display is received while the proximity-sensitive display is presenting one or more items. In one aspect, the techniques describe may involve a process for disambiguating touch selections of hypothesized items, such as text or graphical objects that have been generated based on input data, on a proximity-sensitive display. This process may allow a user to more easily select hypothesized items that the user may wish to correct, by determining whether a touch received through the proximity-sensitive display represents a selection of each hypothesized item based at least on a level of confidence that the hypothesized item accurately represents the input data.
1. A computer-implemented method performed using a system that processes selections of items, the method comprising:
providing an item of information for output at a first location on a display;
receiving data for a user input that includes image data and that was received at a second location on the display;
generating an object tag for the item of information based on objects depicted in the image data;
determining a confidence value that indicates a confidence that the item of information accurately represents a particular type of input based on a recognition process that was used to generate the object tag;
determining whether the user input represents a selection of the item of information based at least on:
(i) the confidence value, and
(ii) the second location of the user input; and
providing an indication of whether the user input represents selection of the item of information.
2. The computer-implemented method of claim 1 , further comprising:
receiving, at the system, the particular type of input;
generating text for the item of information as a representation of the received particular type of input; and
determining the confidence value based on a mapping process used to generate the text.
3. The computer-implemented method of claim 1 , wherein the particular type of user input includes audio data and the method further comprises:
generating a transcription as a representation of the audio data, wherein the transcription corresponds to the item of information; and
determining the confidence value based on a mapping process used to generate the transcription.
4. The computer-implemented method of claim 1 , wherein generating the object tag comprises:
generating the object tag as a graphic superimposed onto an image rendered using the image data; and
causing the object tag to be positioned over an object in the image, the object in the image corresponding to a biometric feature of a person.
5. The computer-implemented method of claim 1 , wherein determining whether the user input represents the selection of the item of information further comprises:
computing a distance between the first location and the second location; and
determining whether the user input represents the selection of the item of information based on the distance between the first location and the second location.
6. A computer-implemented method comprising:
providing an item of information for output at a first location on a display;
receiving data for a user input received at a second location on the display;
determining a confidence value that indicates a confidence that the item of information accurately represents a particular type of input determining whether the user input represents a selection of the item of information based at least on:
(i) the confidence value, and
(ii) the second location of the user input; and
providing an indication of whether the user input represents selection of the item of information, wherein the particular type of user input corresponds to text in a first language and the method further comprises:
generating the item of information using text in a second language as a translation of the text in a first language; and
determining the confidence value based on a translation process used to obtain the text in the second language.
7. The computer-implemented method of claim 6 , further comprising:
obtaining a geographic location of a device that includes the display;
generating the item of information using text in the second language as the translation of the text in the first language based on the obtained geographic location of the device; and
determining the confidence value based on the translation process and the geographic location of the device.
8. A system comprising:
a processing device;
a non-transitory computer-readable storage device having instructions stored thereon that, when executed by the processing device, causes performance of operations comprising:
providing an item of information for output at a first location on a display;
receiving data for a user input that includes image data and that was received at a second location on the display;
generating an object tag for the item of information based on objects depicted in the image data;
determining a confidence value that indicates a confidence that the item of information accurately represents a particular type of input based on a recognition process that was used to generate the object tag;
determining whether the user input represents a selection of the item of information based at least on:
(i) the confidence value, and
(ii) the second location of the user input; and
providing an indication of whether the user input represents selection of the item of information.
9. The system of claim 8 , wherein the operations further comprises:
receiving, at the system, the particular type of input;
generating text for the item of information as a representation of the received particular type of input; and
determining the confidence value based on a mapping process used to generate the text.
10. The system of claim 8 , wherein the particular type of user input includes audio data and the operations further comprise:
generating a transcription as a representation of the audio data, wherein the transcription corresponds to the item of information; and
determining the confidence value based on a mapping process used to generate the transcription.
11. The system of claim 8 , wherein generating the object tag comprises:
generating the object tag as a graphic superimposed onto an image rendered using the image data; and
causing the object tag to be positioned over an object in the image, the object in the image corresponding to a biometric feature of a person.
12. The system of claim 8 , wherein determining whether the user input represents the selection of the item of information further comprises:
computing a distance between the first location and the second location; and
determining whether the user input represents the selection of the item of information based on the distance between the first location and the second location.
13. A system comprising:
a processing device;
a non-transitory computer-readable storage device having instructions stored thereon that, when executed by the processing device, causes performance of operations comprising:
providing an item of information for output at a first location on a display;
receiving data for a user input received at a second location on the display;
determining a confidence value that indicates a confidence that the item of information accurately represents a particular type of input;
determining whether the user input represents a selection of the item of information based at least on:
(i) the confidence value, and
(ii) the second location of the user input; and
providing an indication of whether the user input represents selection of the item of information, wherein the particular type of user input corresponds to text in a first language and the method further comprises:
generating the item of information using text in a second language as a translation of the text in a first language; and
determining the confidence value based on a translation process used to obtain the text in the second language.
14. The system of claim 13 , wherein the operations further comprise:
obtaining a geographic location of a device that includes the display;
generating the item of information using text in the second language as the translation of the text in the first language based on the obtained geographic location of the device; and
determining the confidence value based on the translation process and the geographic location of the device.
15. One or more non-transitory machine-readable storage devices storing instructions that are executable by one or more processing devices to cause performance of operations comprising:
providing an item of information for output at a first location on a display;
receiving data for a user input that includes image data and that was received at a second location on the display;
generating an object tag for the item of information based on objects depicted in the image data;
determining a confidence value that indicates a confidence that the item of information accurately represents a particular type of input based on a recognition process that was used to generate the object tag;
determining whether the user input represents a selection of the item of information based at least on:
(i) the confidence value, and
(ii) the second location of the user input; and
providing an indication of whether the user input represents selection of the item of information.
16. The non-transitory machine-readable storage devices of claim 15 , wherein the particular type of user input includes audio data and the operations further comprise:
generating a transcription as a representation of the audio data, wherein the transcription corresponds to the item of information; and
determining the confidence value based on a mapping process used to generate the transcription.
17. One or more non-transitory machine-readable storage devices storing instructions that are executable by one or more processing devices to cause performance of operations comprising:
providing an item of information for output at a first location on a display;
receiving data for a user input received at a second location on the display;
determining a confidence value that indicates a confidence that the item of information accurately represents a particular type of input;
determining whether the user input represents a selection of the item of information based at least on:
(i) the confidence value, and
(ii) the second location of the user input; and
providing an indication of whether the user input represents selection of the item of information, wherein the particular type of user input corresponds to text in a first language and the method further comprises:
generating the item of information using text in a second language as a translation of the text in a first language; and
determining the confidence value based on a translation process used to obtain the text in the second language.