International Business Machines Corporation
Machine learning on mixed data documents

Abstract:

A first natural language document is received. The document includes unstructured data and a first table structure that includes a plurality of first table entries. The first table structure is identified based on the document. The first table structure is extracted from the document in response to the identifying. A first machine learning output is generated based on a first machine learning model and from the document. A second machine learning output is generated based on a second machine learning model and from the first table structure. The first output of the document and the second output of the first table structure are combined.