https://hackerpaper.kaipfister.de/p/1908.07836/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=38280446urn:hackerpapers:mention:1908.07836:38280446Wed, 15 Nov 2023 18:33:36 GMT<p>Layout analysis is the key. Quite a bit of work has been going on recently in this area. Some papers of relevance: - Xu Zhong, Jianbin Tang, Antonio Jimeno Yepes. &quot;PubLayNet: largest dataset ever for document layout analysis,&quot; Aug 2019. Preprint: https://arxiv.org/abs/1908.07836 Code/Data: https://github.com/ibm-aur-nlp/PubLayNet - B. Pfitzmann, C. Auer, M. Dolfi, A. S. Nassar and P. Staar, &quot;DocLayNet: a large human-annotated dataset for document-layout analysis,&quot; 13 August 2022. [Online]. Available: https://developer.ibm.com/exchanges/data/all/doclaynet/. - S. Appalaraju, B. Jasani, B. U.…</p><p><a href="https://hackerpaper.kaipfister.de/p/1908.07836/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CL