Integrating and querying similar tables from PDF documents using deep learning
This addresses the challenge of consolidating and analyzing semi-structured financial data from PDFs for enterprises, though it is incremental as it builds on existing deep learning techniques for a specific domain.
The paper tackles the problem of querying similar financial tables from PDF documents by proposing a deep learning method for table type classification and nearest row search, demonstrating that word embedding outperforms text-match approaches.
Large amount of public data produced by enterprises are in semi-structured PDF form. Tabular data extraction from reports and other published data in PDF format is of interest for various data consolidation purposes such as analysing and aggregating financial reports of a company. Queries into the structured tabular data in PDF format are normally processed in an unstructured manner through means like text-match. This is mainly due to that the binary format of PDF documents is optimized for layout and rendering and do not have great support for automated parsing of data. Moreover, even the same table type in PDF files varies in schema, row or column headers, which makes it difficult for a query plan to cover all relevant tables. This paper proposes a deep learning based method to enable SQL-like query and analysis of financial tables from annual reports in PDF format. This is achieved through table type classification and nearest row search. We demonstrate that using word embedding trained on Google news for header match clearly outperforms the text-match based approach in traditional database. We also introduce a practical system that uses this technology to query and analyse finance tables in PDF documents from various sources.