Seg2Act: Global Context-aware Action Generation for Document Logical Structuring

TL;DR

Seg2Act is a novel generation-based approach that models document logical structuring as an action sequence generation task, effectively capturing global context to improve hierarchical document understanding.

Contribution

It introduces Seg2Act, an end-to-end method that iteratively generates logical structure actions using global context, outperforming traditional methods on key datasets.

Findings

Superior performance on ChCatExt and HierDoc datasets

Effective in both supervised and transfer learning settings

Outperforms existing approaches in document hierarchy extraction

Abstract

Document logical structuring aims to extract the underlying hierarchical structure of documents, which is crucial for document intelligence. Traditional approaches often fall short in handling the complexity and the variability of lengthy documents. To address these issues, we introduce Seg2Act, an end-to-end, generation-based method for document logical structuring, revisiting logical structure extraction as an action generation task. Specifically, given the text segments of a document, Seg2Act iteratively generates the action sequence via a global context-aware generative model, and simultaneously updates its global context and current logical structure based on the generated actions. Experiments on ChCatExt and HierDoc datasets demonstrate the superior performance of Seg2Act in both supervised and transfer learning settings.