Ceramic
发表于 2025-3-23 10:28:24
http://reply.papertrans.cn/29/2824/282305/282305_11.png
闯入
发表于 2025-3-23 16:48:50
DAMGCN: Entity Linking in Visually Rich Documents with Dependency-Aware Multimodal Graph Convolution the public FUNSD and XFUND datasets show that our DAMGCN achieves competitive results, i.e., F1 scores of 0.8063 and 0.7303 in entity linking tasks, respectively, while the model size is much smaller than the state-of-the-art models.
floaters
发表于 2025-3-23 20:03:10
http://reply.papertrans.cn/29/2824/282305/282305_13.png
EXPEL
发表于 2025-3-24 01:14:45
http://reply.papertrans.cn/29/2824/282305/282305_14.png
ABYSS
发表于 2025-3-24 06:11:09
http://reply.papertrans.cn/29/2824/282305/282305_15.png
licence
发表于 2025-3-24 06:50:33
http://reply.papertrans.cn/29/2824/282305/282305_16.png
narcotic
发表于 2025-3-24 13:45:35
http://reply.papertrans.cn/29/2824/282305/282305_17.png
恭维
发表于 2025-3-24 18:49:33
http://reply.papertrans.cn/29/2824/282305/282305_18.png
Melatonin
发表于 2025-3-24 21:37:21
CED: Catalog Extraction from Documentshat our proposed method outperforms baseline systems and shows a good ability to transfer. We believe the CED task could fill the gap between raw text segments and information extraction tasks on extremely long documents. Data and code are available at
矛盾心理
发表于 2025-3-25 03:12:33
http://reply.papertrans.cn/29/2824/282305/282305_20.png