Data-Efficient Information Extraction from Form-Like Documents

TL;DR

This paper presents a data-efficient transfer learning approach for extracting information from form-like documents, demonstrating significant improvements with limited labeled data and multi-domain training.

Contribution

It introduces a simple transfer learning method that enhances information extraction accuracy across diverse document types with minimal labeled data.

Findings

Up to 27 F1 point improvement with small training sets using transfer learning.

Additional 8 F1 point gain with multi-domain transfer learning.

Data efficiency and representation learning are key to scaling document information extraction.

Abstract

Automating information extraction from form-like documents at scale is a pressing need due to its potential impact on automating business workflows across many industries like financial services, insurance, and healthcare. The key challenge is that form-like documents in these business workflows can be laid out in virtually infinitely many ways; hence, a good solution to this problem should generalize to documents with unseen layouts and languages. A solution to this problem requires a holistic understanding of both the textual segments and the visual cues within a document, which is non-trivial. While the natural language processing and computer vision communities are starting to tackle this problem, there has not been much focus on (1) data-efficiency, and (2) ability to generalize across different document types and languages. In this paper, we show that when we have only a small number of labeled documents for training (~50), a straightforward transfer learning approach from a considerably structurally-different larger labeled corpus yields up to a 27 F1 point improvement over simply training on the small corpus in the target domain. We improve on this with a simple multi-domain transfer learning approach, that is currently in production use, and show that this yields up to a further 8 F1 point improvement. We make the case that data efficiency is critical to enable information extraction systems to scale to handle hundreds of different document-types, and learning good representations is critical to accomplishing this.