Systems and methods for information extraction from text documents with spatial context

A non-transitory computer-readable storage medium storing instructions that, when executed by a processor, cause a computing device to perform a method for information extraction from an electronic document, by performing the steps of:

• receiving an input document, wherein the input document is a semi-structured document;
• retrieving an entity model from an entity model storage, wherein the entity model provides one or more domain variable definitions for one or more domain variables, wherein the entity model and the input document correspond to a common domain;
• determining that the input document includes an entity that satisfies a first domain variable definition corresponding to a first domain variable;
• retrieving a relational model from a relational model storage, wherein the relational model provides, for the first domain variable, one or more relational definitions for one or more values corresponding to the first domain variable, wherein the one or more relational definitions for the one or more values corresponding to the first domain variable comprise one or more spatial restrictions constrained by a length of a gap between entities, wherein the one or more spatial restrictions are computed based on an average width of a horizontal space between entities for horizontal adjacency or based on average line spacing for vertical adjacency;
• extracting one or more data elements from the input document that satisfy the one or more relational definitions;
• and
• generating an information graph having a structured data format, wherein the one or more data elements extracted from the input document correspond to the first domain variable in the structured data format.

A computing device, comprising:

• a memory storing instructions;
• and
• a processor configured to execute the instructions to cause the computing device to perform information extraction from an electronic document by:
• receiving an input document, wherein the input document is a semi-structured document;
• retrieving an entity model from an entity model storage, wherein the entity model provides one or more domain variable definitions for one or more domain variables, wherein the entity model and the input document correspond to a common domain;
• determining that the input document includes an entity that satisfies a first domain variable definition corresponding to a first domain variable;
• retrieving a relational model from a relational model storage, wherein the relational model provides, for the first domain variable, one or more relational definitions for one or more values corresponding to the first domain variable, wherein the one or more relational definitions for the one or more values corresponding to the first domain variable comprise one or more spatial restrictions constrained by a length of a gap between entities, wherein the one or more spatial restrictions are computed based on an average width of a horizontal space between entities for horizontal adjacency or based on average line spacing for vertical adjacency;
• extracting one or more data elements from the input document that satisfy the one or more relational definitions;
• and
• generating an information graph having a structured data format, wherein the one or more data elements extracted from the input document correspond to the first domain variable in the structured data format.