A Machine Learning Framework for Data Ingestion in Document Images
This addresses data ingestion needs in fields like finance where paper documents are prevalent, but it appears incremental as it builds on existing solutions without claiming major breakthroughs.
The authors tackled the problem of converting document images into structured data representations, presenting a machine learning framework that processes uploaded images and returns fine-grained JSON data, with experiments on synthetic and real-world data from State Street showing effectiveness and efficiency.
Paper documents are widely used as an irreplaceable channel of information in many fields, especially in financial industry, fostering a great amount of demand for systems which can convert document images into structured data representations. In this paper, we present a machine learning framework for data ingestion in document images, which processes the images uploaded by users and return fine-grained data in JSON format. Details of model architectures, design strategies, distinctions with existing solutions and lessons learned during development are elaborated. We conduct abundant experiments on both synthetic and real-world data in State Street. The experimental results indicate the effectiveness and efficiency of our methods.