Irreflexive and Hierarchical Relations as Translations

By Antoine Bordes, Nicolas Usunier, Alberto García-Durán, Jason Aaron Edward Weston, Oksana Yakhnenko. 2013

36 citations recorded by the source corpus.

We consider the problem of embedding entities and relations of knowledge bases in lowdimensional vector spaces. Unlike most existing approaches, which are primarily efficient for modeling equivalence relations, our approach is designed to explicitly model irreflexive relations, such as hierarchies, by interpreting them as translations operating on the low-dimensional embeddings of the entities. Preliminary experiments show that, despite its simplicity and a smaller number of parameters than previous approaches, our approach achieves state-of-the-art performance according to standard evaluation protocols on data from WordNet and Freebase.

Subfields: Artificial Intelligence, Information Systems, Knowledge Graphs & Representation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

In Knowledge Graphs & Representation

Citations in the corpus

Knowledge Graph Embedding by Translating on Hyperplanes (2014, methodology): “Please refer to the Introduction part of (Bordes et al. 2013b).”
Connecting Language and Knowledge Bases with Embedding Models for Relation Extraction (2013, methodology): “See (Weston et al., 2010; Bordes et al., 2013) for details.”
Complex Embeddings for Simple Link Prediction (2016, methodology): “The TransE model from Bordes et al. (2013b) also embeds entities and relations in the same space and imposes a geometrical structural bias into the model: the subject entity vector should be close to the object entity vector once translated by the relation vector.”
SimplE Embedding for Link Prediction in Knowledge Graphs (2018, background): “As described in [3], to scale to the size of the current KGs and keep up with their growth, a relational model must have a linear time and memory complexity.”
Knowledge Graph Completion via Complex Tensor Factorization (2017, methodology): “The TransE model from Bordes et al. (2013b) also embeds entities and relations in the same space and imposes a geometrical structural bias into the model: the subject entity vector should be close to the object entity vector once translated by the relation vector.”
Discrete-State Variational Autoencoders for Joint Discovery and Factorization of Relations (2016, background): “…or tensor factorization has received a lot of attention in the past few years (Bordes et al., 2011; Jenatton et al., 2012; Weston et al., 2013; Bordes et al., 2013; Socher et al., 2013; Garcı́a-Durán et al., 2014; Bordes et al., 2014; Lin et al., 2015b; Chang et al., 2014; Nickel et al.,…”
Reasoning With Neural Tensor Networks for Knowledge Base Completion (2013, methodology): “[17] these factorization methods have been outperformed by energybased models.”