Timezone: »
Knowledge base completion (KBC) aims to automatically infer missing facts by exploiting information already present in a knowledge base (KB). A promising approach for KBC is to embed knowledge into latent spaces and make predictions from learned embeddings. However, existing embedding models are subject to at least one of the following limitations: (1) theoretical inexpressivity, (2) lack of support for prominent inference patterns (e.g., hierarchies), (3) lack of support for KBC over higher-arity relations, and (4) lack of support for incorporating logical rules. Here, we propose a spatio-translational embedding model, called BoxE, that simultaneously addresses all these limitations. BoxE embeds entities as points, and relations as a set of hyper-rectangles (or boxes), which spatially characterize basic logical properties. This seemingly simple abstraction yields a fully expressive model offering a natural encoding for many desired logical properties. BoxE can both capture and inject rules from rich classes of rule languages, going well beyond individual inference patterns. By design, BoxE naturally applies to higher-arity KBs. We conduct a detailed experimental analysis, and show that BoxE achieves state-of-the-art performance, both on benchmark knowledge graphs and on more general KBs, and we empirically show the power of integrating logical rules.
Author Information
Ralph Abboud (University of Oxford)
Ismail Ceylan (University of Oxford)
Thomas Lukasiewicz (University of Oxford)
Tommaso Salvatori (University of Oxford)
Related Events (a corresponding poster, oral, or spotlight)
-
2020 Poster: BoxE: A Box Embedding Model for Knowledge Base Completion »
Wed Dec 9th 05:00 -- 07:00 PM Room Poster Session 3
More from the Same Authors
-
2020 Poster: Lightweight Generative Adversarial Networks for Text-Guided Image Manipulation »
Bowen Li · Xiaojuan Qi · Philip Torr · Thomas Lukasiewicz -
2020 Poster: Coherent Hierarchical Multi-Label Classification Networks »
Eleonora Giunchiglia · Thomas Lukasiewicz -
2020 Poster: Can the Brain Do Backpropagation? --- Exact Implementation of Backpropagation in Predictive Coding Networks »
Yuhang Song · Thomas Lukasiewicz · Zhenghua Xu · Rafal Bogacz -
2019 Poster: Controllable Text-to-Image Generation »
Bowen Li · Xiaojuan Qi · Thomas Lukasiewicz · Philip Torr -
2018 Poster: e-SNLI: Natural Language Inference with Natural Language Explanations »
Oana-Maria Camburu · Tim Rocktäschel · Thomas Lukasiewicz · Phil Blunsom