Spatial Dependency Parsing for Semi-Structured Document Information Extraction
This addresses the problem of extracting structured information from real-world document images for applications like data processing, though it is an incremental improvement over existing methods.
The paper tackled the limitations of sequence tagging for information extraction from semi-structured document images by formulating it as a spatial dependency parsing problem, and the proposed SPADE method achieved similar or better performance compared to strong baselines like BERT-based IOB taggers on documents such as receipts and invoices.
Information Extraction (IE) for semi-structured document images is often approached as a sequence tagging problem by classifying each recognized input token into one of the IOB (Inside, Outside, and Beginning) categories. However, such problem setup has two inherent limitations that (1) it cannot easily handle complex spatial relationships and (2) it is not suitable for highly structured information, which are nevertheless frequently observed in real-world document images. To tackle these issues, we first formulate the IE task as spatial dependency parsing problem that focuses on the relationship among text tokens in the documents. Under this setup, we then propose SPADE (SPAtial DEpendency parser) that models highly complex spatial relationships and an arbitrary number of information layers in the documents in an end-to-end manner. We evaluate it on various kinds of documents such as receipts, name cards, forms, and invoices, and show that it achieves a similar or better performance compared to strong baselines including BERT-based IOB taggger.