Techniques of information extraction for selection marks

A computing system, comprising:

• one or more processors;
• and
• a non-transitory computer-readable medium containing instructions that, when executed by the one or more processors, cause the system to perform operations to:
• receive, by the computing system, a primary document comprising one or more selection boxes, one or more text lines, and one or more annotations;
• determine, by the computing system, a class based at least in part on the annotations;
• determine, by the computing system, the one or more selection boxes and one or more text lines associated with the class;
• generate, by the computing system, a graph representing the one or more selection boxes and the one or more text lines;
• map, by the computing system, each of the one or more selection boxes to a respective text line of the one or more text lines of the graph, based at least in part on one or more characteristics associated with the selection boxes;
• generate, by the computing system, a key-value pair for each of the one or more text lines based at least in part on the mapping, wherein the key is the class and the value is an associated text line;
• and
• generate, by the computing system, a document model of the primary document including the key-value pairs.

A non-transitory computer readable medium comprising instructions that, when executed by one or more processors, cause the one or more processors to perform steps comprising:

• receiving, by a computing system, a primary document comprising one or more selection boxes, one or more text lines, and one or more annotations;
• determining, by the computing system, a class based at least in part on the annotations;
• determining, by the computing system, the one or more selection boxes and one or more text lines associated with the class;
• generating, by the computing system, a graph representing the one or more selection boxes and the one or more text lines;
• mapping, by the computing system, each of the one or more selection boxes to a respective text line of the one or more text lines of the graph, based at least in part on one or more characteristics associated with the selection boxes;
• generating, by the computing system, a key-value pair for each of the one or more text lines based at least in part on the mapping, wherein the key is the class and the value is an associated text line;
• and
• generating, by the computing system, a document model of the primary document including the key-value pairs.