Feature-based autocorrection
First Claim
1. A method comprising:
- receiving, by a computing device, a first user input at a keyboard;
responsive to receiving the first user input, outputting, by the computing device, for display, based on the first user input, an initial word from a lexicon;
responsive to receiving a second user input at the keyboard, outputting, by the computing device, for display, and based on the second user input, one or more subsequent words from the lexicon;
while displaying the initial word and the one or more subsequent words, determining, by the computing device, based on the one or more subsequent words, a language model probability associated with at least one candidate word that is determined to be a replacement for the initial word, wherein the language model probability associated with the at least one candidate word represents a likelihood that the at least one candidate word is a correct spelling of the initial word in a sequence of words in which the one or more subsequent words follow the initial word;
determining whether the language model probability associated with the at least one candidate word satisfies a threshold;
responsive to determining that the language model probability associated with the at least one candidate word satisfies the threshold, outputting, by the computing device, for display, the at least one candidate word within a predefined distance above, below, or adjacent to the initial word;
determining, by the computing device, based on a third user input, a selection of the at least one candidate word;
responsive to determining the selection of the at least one candidate word;
refraining from outputting, by the computing device, for display, the at least one candidate word within the predefined distance above, below, or adjacent to the initial word; and
outputting, by the computing device, for display, the at least one candidate word in place of the initial word.
2 Assignments
0 Petitions
Accused Products
Abstract
A computing device is described that outputs for display at a presence-sensitive screen, a graphical keyboard having keys. The computing device receives an indication of a selection of one or more of the keys. Based on the selection the computing device determines a character string from which the computing device determines one or more candidate words. Based at least in part on the candidate words and a plurality of features, the computing device determines a spelling probability that the character string represents an incorrect spelling of at least one candidate word. The plurality of features includes a spatial model probability associated with at least one of the candidate words. If the spelling probability satisfies a threshold, the computing device outputs for display the at least one candidate word.
102 Citations
16 Claims
-
1. A method comprising:
-
receiving, by a computing device, a first user input at a keyboard; responsive to receiving the first user input, outputting, by the computing device, for display, based on the first user input, an initial word from a lexicon; responsive to receiving a second user input at the keyboard, outputting, by the computing device, for display, and based on the second user input, one or more subsequent words from the lexicon; while displaying the initial word and the one or more subsequent words, determining, by the computing device, based on the one or more subsequent words, a language model probability associated with at least one candidate word that is determined to be a replacement for the initial word, wherein the language model probability associated with the at least one candidate word represents a likelihood that the at least one candidate word is a correct spelling of the initial word in a sequence of words in which the one or more subsequent words follow the initial word; determining whether the language model probability associated with the at least one candidate word satisfies a threshold; responsive to determining that the language model probability associated with the at least one candidate word satisfies the threshold, outputting, by the computing device, for display, the at least one candidate word within a predefined distance above, below, or adjacent to the initial word; determining, by the computing device, based on a third user input, a selection of the at least one candidate word; responsive to determining the selection of the at least one candidate word; refraining from outputting, by the computing device, for display, the at least one candidate word within the predefined distance above, below, or adjacent to the initial word; and outputting, by the computing device, for display, the at least one candidate word in place of the initial word. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. A computing device comprising:
-
at least one processor; and a memory comprising instructions that, when executed, cause the at least one processor to; receive a first user input at a keyboard; responsive to receiving the first user input, output, for display, based on the first user input, an initial word from a lexicon; responsive to receiving a second user input at the keyboard, output, for display, and based on the second user input, one or more subsequent words from the lexicon; while displaying the initial word and the one or more subsequent words, determine, based on at least one of the one or more subsequent words, a language model probability associated with at least one candidate word that is determined to be a replacement for the initial word, wherein the language model probability associated with the at least one candidate word represents a likelihood that the at least one candidate word is a correct spelling of the initial word in a sequence of words in which the one or more subsequent words follow the initial word; determine whether the language model probability associated with the at least one candidate word satisfies a threshold; responsive to determining that the language model probability associated with the at least one candidate word satisfies the threshold, output, for display, at an initial point in time, the at least one candidate word determine whether an elapsed time between the initial point in time and a later point in time exceeds a time threshold; and responsive to determining that the elapsed time between the initial point in time and the later point in time exceeds the time threshold, refraining from outputting, for display, the at least one candidate word. - View Dependent Claims (10, 11, 12)
-
-
13. A computer-readable storage medium comprising instructions that, when executed, configure at least one processor of a computing device to:
-
receive a first user input at a keyboard; responsive to receiving the first indication, output, for display, based on the first user input, an initial word from a lexicon; responsive to receiving a second user input at the keyboard, output, for display, and based on the second user input, one or more subsequent words from the lexicon; while displaying the initial word and the one or more subsequent words, determine, based on at least one of the one or more subsequent words, a language model probability associated with at least one candidate word that is determined to be a replacement for the initial word, wherein the language model probability associated with the at least one candidate word represents a likelihood that the at least one candidate word is a correct spelling of the initial word in a sequence of words in which the one or more subsequent words follow the initial word; determine whether the language model probability associated with the at least one candidate word satisfies a threshold; responsive to determining that the language model probability associated with the at least one candidate word satisfies the threshold, output, for display, at an initial point in time, the at least one candidate word determine whether an elapsed time between the initial point in time and a later point in time exceeds a time threshold; and responsive to determining that the elapsed time between the initial point in time and the later point in time exceeds the time threshold, refraining from outputting, for display, the at least one candidate word. - View Dependent Claims (14, 15, 16)
-
Specification