Text-Graph Enhanced Knowledge Graph Representation Learning

Frontiers in Artificial Intelligence

Chuan Shi¹  Mengmei Zhang¹  Linmei Hu¹  Jinghan Shi¹  Cheng Yang¹  Zhiyuan Liu²  Shaohua Li³ 

[1] Department Computer Science, Organization Beijing University of Posts and Telecommunications, Beijing, China;Department Computer Science, Organization Tsinghua University, Beijing, China;Department High Performance Computing, Organization A*STAR, Singapore, Singapore;

关键词: knowledge graph;    graph neural networks;    representation learning;    graph;    structure sparsity;   

DOI  :  10.3389/frai.2021.697856

来源: DOAJ

【 摘 要 】

Knowledge Graphs (KGs) such as Freebase and YAGO have been widely adopted in a variety of NLP tasks. Representation learning of Knowledge Graphs (KGs) aims to map entities and relationships into a continuous low-dimensional vector space. Conventional KG embedding methods (such as TransE and ConvE) utilize only KG triplets and thus suffer from structure sparsity. Some recent works address this issue by incorporating auxiliary texts of entities, typically entity descriptions. However, these methods usually focus only on local consecutive word sequences, but seldom explicitly use global word co-occurrence information in a corpus. In this paper, we propose to model the whole auxiliary text corpus with a graph and present an end-to-end text-graph enhanced KG embedding model, named Teger. Specifically, we model the auxiliary texts with a heterogeneous entity-word graph (called text-graph), which entails both local and global semantic relationships among entities and words. We then apply graph convolutional networks to learn informative entity embeddings that aggregate high-order neighborhood information. These embeddings are further integrated with the KG triplet embeddings via a gating mechanism, thus enriching the KG representations and alleviating the inherent structure sparsity. Experiments on benchmark datasets show that our method significantly outperforms several state-of-the-art methods.

【 授权许可】

Unknown