Table-Of-Contents generation on contemporary documents
This addresses a challenging task in document understanding for real-world commercial documents, though it appears incremental as it builds on existing neural approaches.
The paper tackles the problem of generating precise Table-Of-Contents from non-standardized documents with rich layouts, presenting a neural-based pipeline that outperforms state-of-the-art methods on both public and newly released datasets.
The generation of precise and detailed Table-Of-Contents (TOC) from a document is a problem of major importance for document understanding and information extraction. Despite its importance, it is still a challenging task, especially for non-standardized documents with rich layout information such as commercial documents. In this paper, we present a new neural-based pipeline for TOC generation applicable to any searchable document. Unlike previous methods, we do not use semantic labeling nor assume the presence of parsable TOC pages in the document. Moreover, we analyze the influence of using external knowledge encoded as a template. We empirically show that this approach is only useful in a very low resource environment. Finally, we propose a new domain-specific data set that sheds some light on the difficulties of TOC generation in real-world documents. The proposed method shows better performance than the state-of-the-art on a public data set and on the newly released data set.