Machine learning methods and systems for extracting entities from semi-structured enterprise documents

A server system, comprising:

• a communication interface;
• a memory comprising executable instructions;
• and
• a processor communicably coupled to the communication interface and the memory, the processor configured to cause the server system to perform at least:
• receive an enterprise document in a semi-structured format from a user, the enterprise document comprising one or more tokens;
• extract document features from the enterprise document, the document features comprising structural, token-specific, and entity-specific features;
• identify candidate entities in the enterprise document based, at least in part, on a machine learning model which uses the document features, the candidate entities comprising candidate tabular entities and candidate non-tabular entities obtained from the one or more tokens in the enterprise document;
• compute probability scores for the one or more tokens corresponding to the candidate non-tabular entities and the candidate tabular entities, based, at least in part, on the machine learning model;
• and
• extract structured data from the enterprise document according to the identified candidate non-tabular entities and candidate tabular entities based, at least in part, on the probability scores.