Capturing Logical Structure of Visually Structured Documents with Multimodal Transition Parser

Yuta Koreeda, Christopher Manning


Abstract
While many NLP pipelines assume raw, clean texts, many texts we encounter in the wild, including a vast majority of legal documents, are not so clean, with many of them being visually structured documents (VSDs) such as PDFs. Conventional preprocessing tools for VSDs mainly focused on word segmentation and coarse layout analysis, whereas fine-grained logical structure analysis (such as identifying paragraph boundaries and their hierarchies) of VSDs is underexplored. To that end, we proposed to formulate the task as prediction of “transition labels” between text fragments that maps the fragments to a tree, and developed a feature-based machine learning system that fuses visual, textual and semantic cues. Our system is easily customizable to different types of VSDs and it significantly outperformed baselines in identifying different structures in VSDs. For example, our system obtained a paragraph boundary detection F1 score of 0.953 which is significantly better than a popular PDF-to-text tool with an F1 score of 0.739.
Anthology ID:
2021.nllp-1.15
Volume:
Proceedings of the Natural Legal Language Processing Workshop 2021
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic
Editors:
Nikolaos Aletras, Ion Androutsopoulos, Leslie Barrett, Catalina Goanta, Daniel Preotiuc-Pietro
Venue:
NLLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
144–154
Language:
URL:
https://aclanthology.org/2021.nllp-1.15
DOI:
10.18653/v1/2021.nllp-1.15
Bibkey:
Cite (ACL):
Yuta Koreeda and Christopher Manning. 2021. Capturing Logical Structure of Visually Structured Documents with Multimodal Transition Parser. In Proceedings of the Natural Legal Language Processing Workshop 2021, pages 144–154, Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Capturing Logical Structure of Visually Structured Documents with Multimodal Transition Parser (Koreeda & Manning, NLLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.nllp-1.15.pdf
Code
 stanfordnlp/pdf-struct