Querying semantic data from unstructured documents

A system, comprising:

• a memory;
• and
• at least one processor coupled to the memory and configured to:
• perform optical character recognition on a document;
• generate a character grid using character information obtained from the optical character recognition, wherein the character grid is a two-dimensional down-sampled version of the document;
• apply a convolutional neural network (CNN) to the character grid and to a query string;
• and
• in response to the applying, generate a segmentation mask identifying target data of the document corresponding to the query string.

A non-transitory computer-readable device having instructions stored thereon that, when executed by at least one computing device, cause the at least one computing device to perform operations comprising:

• performing optical character recognition on a document;
• generating a character grid using character information obtained from the optical character recognition, wherein the character grid is a two-dimensional down-sampled version of the document;
• applying a convolutional neural network (CNN) to the character grid and to a query string;
• and
• in response to the applying, generating a segmentation mask identifying target data of the document corresponding to the query string.