Robust PDF Document Conversion using Recurrent Neural Networks

Authors

  • Nikolaos Livathinos IBM Research
  • Cesar Berrospi IBM Research
  • Maksym Lysak IBM Research
  • Viktor Kuropiatnyk IBM Research
  • Ahmed Nassar IBM Research
  • Andre Carvalho IBM Research
  • Michele Dolfi IBM Research
  • Christoph Auer IBM Research
  • Kasper Dinkla IBM Research
  • Peter Staar IBM Research

Keywords:

Production Systems, PDF Documents, Deep Learning, Artificial Intelligence, Document Conversion

Abstract

The number of published PDF documents in both the academic and commercial world has increased exponentially in recent decades. There is a growing need to make their rich content discoverable to information retrieval tools. Achieving high-quality semantic searches demands that a document's structural components such as title, section headers, paragraphs, (nested) lists, tables and figures (including their captions) are properly identified. Unfortunately, the PDF format is known to not conserve such structural information because it simply represents a document as a stream of low-level printing commands, in which one or more characters are placed in a bounding box with a particular styling. In this paper, we present a novel approach to document structure recovery in PDF using recurrent neural networks to process the low-level PDF data representation directly, instead of relying on a visual re-interpretation of the rendered PDF page, as has been proposed in previous literature. We demonstrate how a sequence of PDF printing commands can be used as input into a neural network and how the network can learn to classify each printing command according to its structural function in the page. This approach has three advantages: First, it can distinguish among more fine-grained labels (typically 10-20 labels as opposed to 1-5 with visual methods), which results in a more accurate and detailed document structure resolution. Second, it can take into account the text flow across pages more naturally compared to visual methods because it can concatenate the printing commands of sequential pages. Last, our proposed method needs less memory and it is computationally less expensive than visual methods. This allows us to deploy such models in production environments at a much lower cost. Through extensive architectural search in combination with advanced feature engineering, we were able to implement a model that yields a weighted average F1 score of 97% across 17 distinct structural labels. The best model we achieved is currently served in production environments on our Corpus Conversion Service (CCS), which was presented at KDD18. This model enhances the capabilities of CCS significantly, as it eliminates the need for human annotated label ground-truth for every unseen document layout. This proved particularly useful when applied to a huge corpus of PDF articles related to COVID-19.

Downloads

Published

2021-05-18

How to Cite

Livathinos, N., Berrospi, C., Lysak, M., Kuropiatnyk, V., Nassar, A., Carvalho, A., Dolfi, M., Auer, C., Dinkla, K., & Staar, P. (2021). Robust PDF Document Conversion using Recurrent Neural Networks. Proceedings of the AAAI Conference on Artificial Intelligence, 35(17), 15137-15145. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17777

Issue

Section

IAAI Technical Track on Highly Innovative Applications of AI