End-to-End Document Classification and Key Information Extraction using Assignment Optimization
This addresses the problem of automating document processing for forms, which is incremental as it applies optimization techniques to a known bottleneck.
The paper tackled automated document processing by developing an end-to-end system for document classification and key information extraction from forms, achieving a 0.97 F1 score for classification and a mean 0.94 F1 score for extraction.
We propose end-to-end document classification and key information extraction (KIE) for automating document processing in forms. Through accurate document classification we harness known information from templates to enhance KIE from forms. We use text and layout encoding with a cosine similarity measure to classify visually-similar documents. We then demonstrate a novel application of mixed integer programming by using assignment optimization to extract key information from documents. Our approach is validated on an in-house dataset of noisy scanned forms. The best performing document classification approach achieved 0.97 f1 score. A mean f1 score of 0.94 for the KIE task suggests there is significant potential in applying optimization techniques. Abation results show that the method relies on document preprocessing techniques to mitigate Type II errors and achieve optimal performance.