Xiangnan Chen — accepted AI-conference papers

2023

Global Structure Knowledge-Guided Relation Extraction Method for Visually-Rich Document

Xiangnan Chen, Qian Xiao, Juncheng Li, Duo Dong, Jun Lin, Xiaozhong Liu +1

EMNLP 2023long findings

Visual Relation Extraction (VRE) is a powerful means of discovering relationships between entities within visually-rich documents. Existing methods often focus on manipulating entity features to find pairwise relations, yet neglect the more fundamental structural information that links disparate ent…

Cited by 0 Source ↗code ↗Scholar ↗

2022

Meta-Learning Based Knowledge Extrapolation for Knowledge Graphs in the Federated Setting

Mingyang Chen, Wen Zhang, Zhen Yao, Xiangnan Chen, Mengxiao Ding, Fei Huang +1

IJCAI 2022poster

We study the knowledge extrapolation problem to embed new components (i.e., entities and relations) that come with emerging knowledge graphs (KGs) in the federated setting. In this problem, a model trained on an existing KG needs to embed an emerging KG with unseen entities and relations. To solve t…

Cited by 35 Source ↗PDF ↗code ↗Scholar ↗