Zijun Min — accepted AI-conference papers

2023

Exploring Effective Inter-Encoder Semantic Interaction for Document-Level Relation Extraction

Liang Zhang, Zijun Min, Jinsong Su, Pei Yu, Ante Wang, Yidong Chen

IJCAI 2023poster

In document-level relation extraction (RE), the models are required to correctly predict implicit relations in documents via relational reasoning. To this end, many graph-based methods have been proposed for this task. Despite their success, these methods still suffer from several drawbacks: 1) the…

Cited by 5 Source ↗PDF ↗code ↗Scholar ↗

2023

Exploring Self-Distillation Based Relational Reasoning Training for Document-Level Relation Extraction

Liang Zhang, Jinsong Su, Zijun Min, Zhongjian Miao, Qingguo Hu, Biao Fu +2

AAAI 2023technical

Document-level relation extraction (RE) aims to extract relational triples from a document. One of its primary challenges is to predict implicit relations between entities, which are not explicitly expressed in the document but can usually be extracted through relational reasoning. Previous methods…

Cited by 19 Source ↗PDF ↗code ↗Scholar ↗