CoKE: Contextualized Knowledge Graph Embedding

TL;DR

CoKE introduces a novel approach to knowledge graph embedding by utilizing contextualized, dynamic embeddings through Transformer encoders, significantly improving performance in link prediction and path query answering tasks.

Contribution

This work presents the first fully contextualized knowledge graph embedding method using Transformer models, capturing entity and relation meanings in different graph contexts.

Findings

Outperforms state-of-the-art in link prediction tasks.

Achieves 21.0% improvement in H@10 for path query answering.

Demonstrates robustness across various benchmarks.

Abstract

Knowledge graph embedding, which projects symbolic entities and relations into continuous vector spaces, is gaining increasing attention. Previous methods allow a single static embedding for each entity or relation, ignoring their intrinsic contextual nature, i.e., entities and relations may appear in different graph contexts, and accordingly, exhibit different properties. This work presents Contextualized Knowledge Graph Embedding (CoKE), a novel paradigm that takes into account such contextual nature, and learns dynamic, flexible, and fully contextualized entity and relation embeddings. Two types of graph contexts are studied: edges and paths, both formulated as sequences of entities and relations. CoKE takes a sequence as input and uses a Transformer encoder to obtain contextualized representations. These representations are hence naturally adaptive to the input, capturing contextual meanings of entities and relations therein. Evaluation on a wide variety of public benchmarks verifies the superiority of CoKE in link prediction and path query answering. It performs consistently better than, or at least equally well as current state-of-the-art in almost every case, in particular offering an absolute improvement of 21.0% in H@10 on path query answering. Our code is available at \url{https://github.com/PaddlePaddle/Research/tree/master/KG/CoKE}.