Model-based automatic correction of typographical errors

A computer, comprising:

• one or more processors;
• memory;
• and
• one or more programs stored in the memory that, when executed by the one or more processors, cause the computer to perform the following operations:
• receiving a target sentence entered by a user on a user interface of a text-processing program;
• identifying a target word in the target sentence as having a typographical error in accordance with first predefined criteria;
• selecting, within the target sentence, a first sequence of words that precede the target word and a second sequence of words that succeed the target word according to semantic features of the target word;
• identifying, among a database of grammatically correct sentences, a set of sentences, each sentence including a replacement word that is located after the first sequence of words and before the second sequence of words like the target sentence;
• selecting, from the identified set of grammatically correct sentences, a set of candidate grammatically correct sentences whose corresponding replacement words have similarities to the target word above a pre-set threshold according to second predefined criteria;
• choosing, among the set of candidate grammatically correct sentences, a fittest grammatically correct sentence according to a linguistic model;
• and
• replacing, using the text-processing program, the target word in the target sentence with the replacement word within the fittest grammatically correct sentence.

A non-transitory computer readable storage medium, storing one or more programs for execution by one or more processors of a computer, the one or more programs including instructions for:

• receiving a target sentence entered by a user on a user interface of a text-processing program;
• identifying a target word in the target sentence as having a typographical error in accordance with first predefined criteria;
• selecting, within the target sentence, a first sequence of words that precede the target word and a second sequence of words that succeed the target word according to semantic features of the target word;
• identifying, among a database of grammatically correct sentences, a set of sentences, each sentence including a replacement word that is located after the first sequence of words and before the second sequence of words like the target sentence;
• selecting, from the identified set of grammatically correct sentences, a set of candidate grammatically correct sentences whose corresponding replacement words have similarities to the target word above a pre-set threshold according to second predefined criteria;
• choosing, among the set of candidate grammatically correct sentences, a fittest grammatically correct sentence according to a linguistic model;
• and
• replacing, using the text-processing program, the target word in the target sentence with the replacement word within the fittest grammatically correct sentence.