Lightweight Contextual Logical Structure Recovery

Po-Wei Huang, Abhinav Ramesh Kashyap, Yanxia Qin, Yajing Yang, Min-Yen Kan


Abstract
Logical structure recovery in scientific articles associates text with a semantic section of the article. Although previous work has disregarded the surrounding context of a line, we model this important information by employing line-level attention on top of a transformer-based scientific document processing pipeline. With the addition of loss function engineering and data augmentation techniques with semi-supervised learning, our method improves classification performance by 10% compared to a recent state-of-the-art model. Our parsimonious, text-only method achieves a performance comparable to that of other works that use rich document features such as font and spatial position, using less data without sacrificing performance, resulting in a lightweight training pipeline.
Anthology ID:
2022.sdp-1.5
Volume:
Proceedings of the Third Workshop on Scholarly Document Processing
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Editors:
Arman Cohan, Guy Feigenblat, Dayne Freitag, Tirthankar Ghosal, Drahomira Herrmannova, Petr Knoth, Kyle Lo, Philipp Mayr, Michal Shmueli-Scheuer, Anita de Waard, Lucy Lu Wang
Venue:
sdp
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
37–48
Language:
URL:
https://aclanthology.org/2022.sdp-1.5
DOI:
Bibkey:
Cite (ACL):
Po-Wei Huang, Abhinav Ramesh Kashyap, Yanxia Qin, Yajing Yang, and Min-Yen Kan. 2022. Lightweight Contextual Logical Structure Recovery. In Proceedings of the Third Workshop on Scholarly Document Processing, pages 37–48, Gyeongju, Republic of Korea. Association for Computational Linguistics.
Cite (Informal):
Lightweight Contextual Logical Structure Recovery (Huang et al., sdp 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl-24-ws-corrections/2022.sdp-1.5.pdf