no code implementations • 21 Mar 2024 • Bingchen Liu, Huang Peng, Weixin Zeng, Xiang Zhao, Shijun Liu, Li Pan
MulCanon unifies the learning objectives of these sub-tasks, and adopts a two-stage multi-task learning paradigm for training.
no code implementations • 25 Oct 2023 • Bingchen Liu, Shihao Hou, Weixin Zeng, Xiang Zhao, Shijun Liu, Li Pan
MulCanon unifies the learning objectives of diffusion model, KGE and clustering algorithms, and adopts a two-step multi-task learning paradigm for training.
no code implementations • 7 Jun 2021 • Hao Guo, Jiuyang Tang, Weixin Zeng, Xiang Zhao, Li Liu
To mitigate this problem, a viable approach is to integrate complementary knowledge from other MMKGs.
1 code implementation • 26 Jan 2021 • Weixin Zeng, Xiang Zhao, Jiuyang Tang, Xinyi Li, Minnan Luo, Qinghua Zheng
These preliminary results are regarded as the pseudo-labeled data and forwarded to the progressive learning framework to generate structural representations, which are integrated with the side information to provide a more comprehensive view for alignment.
1 code implementation • 5 Jan 2021 • Weixin Zeng, Xiang Zhao, Jiuyang Tang, Xuemin Lin, Paul Groth
Entity alignment (EA) is the task of identifying the entities that refer to the same real-world object but are located in different knowledge graphs (KGs).
1 code implementation • 25 May 2020 • Weixin Zeng, Xiang Zhao, Wei Wang, Jiuyang Tang, Zhen Tan
Entity alignment (EA) is to discover equivalent entities in knowledge graphs (KGs), which bridges heterogeneous sources of information and facilitates the integration of knowledge.
no code implementations • LREC 2020 • Weixin Zeng, Xiang Zhao, Jiuyang Tang, Zhen Tan, Xuqian Huang
Moreover, we devise a measure to evaluate the difficulty of documents with respect to entity linking, which is then used to characterize the corpus.
1 code implementation • 18 Dec 2019 • Weixin Zeng, Xiang Zhao, Jiuyang Tang, Xuemin Lin
Entity alignment (EA) identifies entities that refer to the same real-world object but locate in different knowledge graphs (KGs), and has been harnessed for KG construction and integration.