A system is described that enables an input method editor (IME) on a computing device (e.g., a wearable device or a mobile device) that provides multiple hypotheses. There are various different mechanisms for inputting a user’s input on a device, such as touch and swipe typing, voice input, handwriting recognition, camera input, optical character recognition (OCR), etc. The device may enable an IME to process a user’s input and return, to an application, multiple hypotheses in a standardized machine-readable form based on the input. The application may select one of the returned hypotheses to use as final input. By enabling the IME to return multiple hypotheses based on a user’s input, the device enables the application to use multiple hypotheses to provide an improved (e.g., more accurate) result.

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.