Abstract: Systems and methods are disclosed for generating a Natural Language Processing (NLP) model through iterative training. A method involves processing a plurality of real-world documents, each containing text data, layout data, and image data, using at least one hardware processor. An initial prediction for data points within the documents is generated using a neural network. The initial prediction is then validated by comparing extracted values with the information present in the documents and correcting any discrepancies. The quality of the NLP model is evaluated based on the validated predictions, and upon satisfying a quality constraint, the NLP model is configured to process new documents to extract data points without further validation. This method streamlines the extraction of information from diverse document formats, enhancing the efficiency and accuracy of data retrieval in automated systems.

Abstract: Methods, systems, and computer programs are presented for providing access to a cloud data platform including a machine learning model for performing a plurality of iterations, by at least one hardware processor, to generate a Natural Language Processing (NLP) model. The cloud data platform performs each iteration by receiving real-world documents and enabling information retrieval from the real-world documents without annotated training data. Each iteration includes receiving data comprising text data, layout data, and image data and analyzing the text data, the layout data, and the image data. The cloud data platform generates one or more outputs from the machine learning model by applying the iterative training on new data, based at least in part on the analyzing of the text data, the layout data, and the image data.

Abstract: Methods, systems, and computer programs are presented for providing access to a cloud data platform including a machine learning model for performing a plurality of iterations, by at least one hardware processor, to generate a Natural Language Processing (NLP) model. The cloud data platform performs each iteration by receiving real-world documents and enabling information retrieval from the real-world documents without annotated training data. Each iteration includes receiving data comprising text data, layout data, and image data and analyzing the text data, the layout data, and the image data. The cloud data platform generates one or more outputs from the machine learning model by applying the iterative training on new data, based at least in part on the analyzing of the text data, the layout data, and the image data.