GFTE: Graph-based Financial Table Extraction
This addresses the challenge of table extraction in finance and other fields where data is often in PDFs or images, though it appears incremental as it builds on existing deep learning approaches.
The authors tackled the problem of extracting structured data from financial tables in unstructured digital files by publishing FinTab, a Chinese dataset with over 1,600 tables, and proposing GFTE, a graph-based CNN model that integrates multiple features for edge prediction with overall good results.
Tabular data is a crucial form of information expression, which can organize data in a standard structure for easy information retrieval and comparison. However, in financial industry and many other fields tables are often disclosed in unstructured digital files, e.g. Portable Document Format (PDF) and images, which are difficult to be extracted directly. In this paper, to facilitate deep learning based table extraction from unstructured digital files, we publish a standard Chinese dataset named FinTab, which contains more than 1,600 financial tables of diverse kinds and their corresponding structure representation in JSON. In addition, we propose a novel graph-based convolutional neural network model named GFTE as a baseline for future comparison. GFTE integrates image feature, position feature and textual feature together for precise edge prediction and reaches overall good results.