Generating programs using context-free compositions and probability of determined transformation rules

A method for generating a program, comprising:

• determining a plurality of rules for a plurality of transformations to transform input data to corresponding output data, based on cues comprising textual features within the input data and the corresponding output data;
• ranking each of the rules according to a probability that one of the plurality of rules explains one of the transformations from the input data to the corresponding output data;
• presenting a user interface comprising a representation of the ranking, and enabling selection of the rules for each transformation;
• and
• generating a program comprising the selected rules.

A program generation system, comprising:

• a processor that is adapted to execute stored instructions;
• and
• a system memory, the system memory comprising code configured to:
• determine a plurality of rules for a plurality of transformations to transform input data to corresponding output data, based on cues comprising textual features within the input data and the corresponding output data;
• rank each of the rules according to a probability that a rule explains a transformation from the input data to the corresponding output data;
• present a user interface comprising a representation of the ranking, and enabling selection of the rules for each transformation;
• and
• generate a program comprising the selected rules, wherein the program is generated by combining the rules in a predetermined order.

One or more computer-readable hardware memory devices for storing computer-readable instructions, the computer-readable instructions providing a program generation system that, when executed by one or more processing devices:

• determines a plurality of rules for a plurality of transformations to transform input data to corresponding output data, based on cues comprising textual features within the input data and the corresponding output data;
• ranks each of the rules according to a probability that a rule explains a transformation from the input data to the corresponding output data;
• presents a user interface comprising a representation of the ranking, and enabling selection of the rules for each transformation;
• and
• generates a program comprising the selected rules, wherein the program is generated by combining the rules in a predetermined order, and wherein the user interface enables manual entry of the input data and the output data.