Hierarchical Neighbor Propagation With Bidirectional Graph Attention Network for Relation Prediction

no code implementations • IEEE/ACM Transactions on Audio, Speech, and Language Processing 2021 • Zhiwen Xie, Runjie Zhu, Jin Liu, Guangyou Zhou, and Jimmy Xiangji Huang

Abstract—The graph attention network (GAT) [1] has started to become a mainstream neural network architecture since 2018, yielding remarkable performance gains in various natural language processing (NLP) tasks.

Graph Attention Relation

A Contextual Alignment Enhanced Cross Graph Attention Network for Cross-lingual Entity Alignment

no code implementations • COLING 2020 • Zhiwen Xie, Runjie Zhu, Kunsong Zhao, Jin Liu, Guangyou Zhou, Jimmy Xiangji Huang

In this paper, we propose a novel Contextual Alignment Enhanced Cross Graph Attention Network (CAECGAT) for the task of cross-lingual entity alignment, which is able to jointly learn the embeddings in different KGs by propagating cross-KG information through pre-aligned seed alignments.

Entity Alignment Graph Attention