Fetching the paper…

Reading the bibliography…

2013

Irreflexive and Hierarchical Relations as Translations

Bordes, Antoine, Usunier, Nicolas, Garcia-Duran, Alberto et al.

Original
PDF
Post on X

Understand

We consider the problem of embedding entities and relations of knowledge bases in low-dimensional 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.

Irreflexive and Hierarchical Relations as Translations · Around

Built on

Parafac: parallel factor analysis
Harshman, Richard A. and Lundy, Margaret E · 1994
Earlier work this paper cites.
Learning systems of concepts with an infinite relational model
Kemp, Charles, Tenenbaum, Joshua B., Griffiths, Thomas L., Yamada, Takeshi, and Ueda, Naonori · 2006
Earlier work this paper cites.
Statistical predicate invention
Kok, Stanley and Domingos, Pedro · 2007
Earlier work this paper cites.
Modelling relational data using bayesian clustered tensor factorization
Sutskever, Ilya, Salakhutdinov, Ruslan, and Tenenbaum, Josh · 2009
Earlier work this paper cites.

Similar

Learning structured embeddings of knowledge bases
Bordes, A., Weston, J., Collobert, R., and Bengio, Y · 2011
Cited alongside, same era.
A three-way model for collective learning on multi-relational data
Nickel, Maximilian, Tresp, Volker, and Kriegel, Hans-Peter · 2011
Cited alongside, same era.
A latent factor model for highly multi-relational data
Jenatton, Rodolphe, Le Roux, Nicolas, Bordes, Antoine, Obozinski, Guillaume, et al · 2012
Cited alongside, same era.

Then

A semantic matching energy function for learning with multi-relational data
Bordes, Antoine, Glorot, Xavier, Weston, Jason, and Bengio, Yoshua · 2013
Closest in time.
Learning new facts from knowledge bases with neural tensor networks and semantic word vectors
Original
Chen, Danqi, Socher, Richard, Manning, Christopher D, and Ng, Andrew Y · 2013
Closest in time.
Efficient estimation of word representations in vector space
Original
Mikolov, Tomas, Chen, Kai, Corrado, Greg, and Dean, Jeffrey · 2013
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…