Identifying an accurate transcription from probabilistic inputs

A computer program product for identifying an accurate transcription of a sentence, the computer program product comprising a computer readable storage medium having computer readable program code stored on the computer readable storage medium, wherein the computer readable storage medium is not a transitory signal per se, the computer readable program code being executed by a central processing unit (CPU) of a computer system to cause the computer system to perform a method comprising the steps of:

• the computer system determining multiple options for transcriptions of each word included in the words in the sentence initially received as written text or speech;
• the computer system determining probabilistic scores of the options, the probabilistic scores indicating respective likelihoods that the multiple options are accurate transcriptions of each word;
• the computer system generating variations of a transcription of the sentence by selecting from the among the multiple options for the transcriptions of each word by using numbers generated by a hardware random number generator or a pseudorandom number generator, the selecting being weighted by the probabilistic scores;
• the computer system generating plausibility scores for the variations by performing syntactic, semantic, and redundancy analyses of the variations, the plausibility scores indicating respective likelihoods that the variations are plausible sentences;
• and
• based on the plausibility scores, the probabilistic scores, and the variations, the computer system determining and refining tentative transcriptions of the sentence repeatedly until a final refined tentative transcription is the accurate transcription of the sentence by employing a genetic evolution technique on the variations.

A computer system comprising:

• a central processing unit (CPU);
• a memory coupled to the CPU;
• and
• a computer readable storage medium coupled to the CPU, the computer readable storage medium containing instructions that are executed by the CPU via the memory to implement a method of identifying an accurate transcription of a sentence, the method comprising the steps of:
• the computer system determining multiple options for transcriptions of each word included in the words in the sentence initially received as written text or speech;
• the computer system determining probabilistic scores of the options, the probabilistic scores indicating respective likelihoods that the multiple options are accurate transcriptions of each word;
• the computer system generating variations of a transcription of the sentence by selecting from the among the multiple options for the transcriptions of each word by using numbers generated by a hardware random number generator or a pseudorandom number generator, the selecting being weighted by the probabilistic scores;
• the computer system generating plausibility scores for the variations by performing syntactic, semantic, and redundancy analyses of the variations, the plausibility scores indicating respective likelihoods that the variations are plausible sentences;
• and
• based on the plausibility scores, the probabilistic scores, and the variations, the computer system determining and refining tentative transcriptions of the sentence repeatedly until a final refined tentative transcription is the accurate transcription of the sentence by employing a genetic evolution technique on the variations.