Techniques for predictive input method editors
First Claim
1. A computer-implemented method comprising:
- receiving, at a computing device comprising one or more processors, a first input from a user, the first input including one or more first characters in a first language;
determining, at the computing device, a plurality of first words in a second language based on the first input, the plurality of first words representing potential transliterations of a plurality of second words from the first language to the second language, respectively, each of the plurality of second words being a potential word beginning with the one or more first characters;
determining, at the computing device, a probability score for each of the plurality of first words using a language model, the probability score for a specific first word indicating a likelihood that (i) a specific second word corresponding to the specific first word is an appropriate word beginning with the one or more first characters and (ii) the specific first word is an appropriate transliteration of the specific second word;
determining, at the computing device, a first sequence of words based on the plurality of first words and their corresponding probability scores, the first sequence of words including the plurality of first words being ordered from a highest relative probability score to a lowest relative probability score;
removing, at the computing device, a first word from the first sequence of words to obtain a modified first sequence of words, the first word having the highest relative probability score;
generating, at the computing device, a second sequence of words based on the modified first sequence of words and an additional word comprising the one or more first characters, the second sequence of words including the additional word as a last word in the second sequence of words;
providing, in a first area of a display of the computing device, the first word from the first sequence of words;
providing, in a second area of the display of the computing device, the second sequence of words and corresponding indications of their relative probability scores, the second area being different than the first area;
receiving, at the computing device, a second input indicating a selection by the user of the first word or one of the second sequence of words, the second input being used to obtain a selected input; and
providing, at the display of the computing device, the selected input.
2 Assignments
0 Petitions
Accused Products
Abstract
A computer-implemented method technique is presented. The technique can include receiving, at a computing device comprising one or more processors, a first input from a user, the first input including one or more first characters in a first language. The technique can provide for suggestion of potential transliterations to a second language of potential words beginning with the one or more first characters. The technique can present the potential transliterations in either an off-the-spot input configuration or an inline input configuration. The user can then select one of the potential transliterations. The technique can also provide the one or more first characters as an additional or partial word as a potential selection for the user. In this manner, the user can also select the exact one or more first characters that were input to the computing device.
33 Citations
20 Claims
-
1. A computer-implemented method comprising:
-
receiving, at a computing device comprising one or more processors, a first input from a user, the first input including one or more first characters in a first language; determining, at the computing device, a plurality of first words in a second language based on the first input, the plurality of first words representing potential transliterations of a plurality of second words from the first language to the second language, respectively, each of the plurality of second words being a potential word beginning with the one or more first characters; determining, at the computing device, a probability score for each of the plurality of first words using a language model, the probability score for a specific first word indicating a likelihood that (i) a specific second word corresponding to the specific first word is an appropriate word beginning with the one or more first characters and (ii) the specific first word is an appropriate transliteration of the specific second word; determining, at the computing device, a first sequence of words based on the plurality of first words and their corresponding probability scores, the first sequence of words including the plurality of first words being ordered from a highest relative probability score to a lowest relative probability score; removing, at the computing device, a first word from the first sequence of words to obtain a modified first sequence of words, the first word having the highest relative probability score; generating, at the computing device, a second sequence of words based on the modified first sequence of words and an additional word comprising the one or more first characters, the second sequence of words including the additional word as a last word in the second sequence of words; providing, in a first area of a display of the computing device, the first word from the first sequence of words; providing, in a second area of the display of the computing device, the second sequence of words and corresponding indications of their relative probability scores, the second area being different than the first area; receiving, at the computing device, a second input indicating a selection by the user of the first word or one of the second sequence of words, the second input being used to obtain a selected input; and providing, at the display of the computing device, the selected input.
-
-
2. A computer-implemented method comprising:
-
receiving, at a computing device comprising one or more processors, a first input from a user, the first input including one or more first characters in a first language; determining, at the computing device, a plurality of first words in a second language based on the first input, the plurality of first words representing potential transliterations of a plurality of second words from the first language to the second language, respectively, each of the plurality of second words being a potential word beginning with the one or more first characters; determining, at the computing device, a probability score for each of the plurality of first words using a language model, the probability score for a specific first word indicating a likelihood that (i) a specific second word corresponding to the specific first word is an appropriate word beginning with the one or more first characters and (ii) the specific first word is an appropriate transliteration of the specific second word; determining, at the computing device, one of the plurality of first words having a highest relative probability score to obtain a selected first word; providing, in a first area of a display of the computing device, the selected first word; and providing, in a second area of the display of the computing device, (i) a remainder of the plurality of first words and corresponding indications of their relative probability scores and (ii) the one or more first characters and a corresponding indication of a lowest relative probability score. - View Dependent Claims (3, 4, 5, 6, 7, 8, 9, 10, 11)
-
-
12. A computing device comprising one or more processors, the computing device further comprising:
-
a user interface configured to receive a first input from a user, the first input including one or more first characters in a first language; and a user interface control module configured to determine a plurality of first words in a second language based on the first input, the plurality of first words representing potential transliterations of a plurality of second words from the first language to the second language, respectively, each of the plurality of second words being a potential word beginning with the one or more first characters, determine a probability score for each of the plurality of first words using a language model, the probability score for a specific first word indicating a likelihood that (i) a specific second word corresponding to the specific first word is an appropriate word beginning with the one or more first characters and (ii) the specific first word is an appropriate transliteration of the specific second word, and determine one of the plurality of first words having a highest relative probability score to obtain a selected first word, wherein the user interface is further configured to provide the selected first word in a first area of a display of the computing device, and to provide (i) a remainder of the plurality of first words and corresponding indications of their relative probability scores and (ii) the one or more first characters and a corresponding indication of a lowest relative probability score, in a second area of the display of the computing device. - View Dependent Claims (13, 14, 15, 16, 17, 18, 19, 20)
-
Specification