Editing Knowledge base completion (state-of-the-art)


== Link (argument) prediction ==

{|class=wikitable
|-
|rowspan="2"| Model
|colspan="2"| WordNet
|colspan="2"| FB13K
|colspan="2"| FB15K (type-constrained) 
|colspan="2"| FB15K (none-constrained) 
|rowspan="2"| Desc. ref.
|rowspan="2"| Perf. ref.
|-
| MRR || HIT@10 || MRR || HIT@10 || MRR || HIT@10 || MRR || HIT@10
|-
| E || - || - || - || - || 22.7 || 34.0 || 21.8 || 33.6 || Riedel et al., 2013<ref>Sebastian Riedel, Limin Yao, Benjamin M. Marlin, and Andrew McCallum. 2013. Relation extraction with matrix factorization and universal schemas. In North American Chapter of the Association for Computational Linguistics: Human Language Tech- nologies (NAACL-HLT).</ref> || Toutanova & Chen (2015)<ref name="toutanova2015">Toutanova, Kristina, and Danqi Chen. "Observed versus latent features for knowledge base and text inference." Proceedings of the 3rd Workshop on Continuous Vector Space Models and their Compositionality. 2015.</ref>
|-
| DistMult || - || - || - || - || 63.1 || 79.0 || 55.5 || 79.7 || Toutanova & Chen (2015) || Toutanova & Chen (2015)
|-
| E+DistMult || - || - || - || - || 65.9 || 81.0 || 56.2 || 78.3 || || Toutanova & Chen (2015)
|-
| Observed (Node+LinkFeat) || - || - || - || - || 82.1 || 86.1 || 82.2 || 87.0 || || Toutanova & Chen (2015)
|-
| DistMult || - || - || - || - || ||  || 36.0 || 57.7 || Yang et al. (2015) || Yang et al. (2015)
|-
| DISTMULT-tanh-EV-init || - || - || - || - || || || 42 || 73.2 || Yang et al. (2015)<ref>Yang, B., Yih, W., He, X., Gao, J., & Deng, L. (2014). Embedding Entities and Relations for Learning and Inference in Knowledge Bases, 12. Computation and Language.</ref> || Yang et al. (2015)
|-
| Unstructured || 315/304 || 35.3/38.2  || -  || -  || -  || - 
| 1,074/979 || 4.5/6.3 
| Bordes et al. 2012<ref>Bordes, A.; Glorot, X.; Weston, J.; and Bengio, Y. 2012. Joint learning of words and meaning representations for open-text semantic parsing. In Proceedings of AISTATS, 127–135.
Bordes,</ref>
| Lin et al. 2015<ref name=lin15/>
|-
| RESCAL  || 1,180/1,163  || 37.2/52.8  || -  || -  || -  || -
| 828/683  || 28.4/44.1 
| Nickel, Tresp, and Kriegel 2011<ref>Nickel, M.; Tresp, V.; and Kriegel, H.-P. 2011. A three- way model for collective learning on multi-relational data. In Proceedings of ICML, 809–816.</ref>
| Lin et al. 2015
|-
| SE || 1,011/985 || 68.5/80.5 || -  || -  || -  || - 
| 273/162  || 28.8/39.8 
| Bordes et al. 2011<ref>Bordes, A.;Weston, J.; Collobert, R.; Bengio,Y.; et al. 2011. Learning structured embeddings of knowledge bases. In Proceedings of AAAI, 301–306.</ref>
| Lin et al. 2015
|-
| SME (linear) || 545/533 || 65.1/74.1 || -  || - || -  || - 
| 274/154 || 30.7/40.8 
| Bordes et al. 2012<ref>Bordes, A.; Glorot, X.; Weston, J.; and Bengio, Y. 2012. Joint learning of words and meaning representations for open-text semantic parsing. In Proceedings of AISTATS, 127–135.</ref>
| Lin et al. 2015
|-
| SME (bilinear) || 526/509 || 54.7/61.3 || -  || -  || -  || - 
| 284/158 || 31.3/41.3 || Bordes et al. 2012
| Lin et al. 2015
|-
| LFM 
| 469/456  || 71.4/81.6 || -  || - || -  || - 
| 283/164  || 26.0/33.1 
| Jenatton et al. 2012<ref>Jenatton, R.; Roux, N. L.; Bordes, A.; and Obozinski, G. R. 2012. A latent factor model for highly multi-relational data. In Proceedings of NIPS, 3167–3175.</ref>
| Lin et al. 2015
|-
| TransE 
| 263/251 || 75.4/89.2 || -  || - ||  -  || -
| 243/125 || 34.9/47.1 || Bordes et al. 2013
| Lin et al. 2015
|-
| TransH (unif) 
| 318/303 || 75.4/86.7 || -  || - ||  -  || - 
| 211/84 || 42.5/58.5 || Wang et al. 2014<ref>Wang, Z.; Zhang, J.; Feng, J.; and Chen, Z. 2014. Knowl- edge graph embedding by translating on hyperplanes. In Proceedings of AAAI, 1112–1119.</ref>
| Lin et al. 2015
|-
| TransH (bern) 
| 401/388 || 73.0/82.3 || -  || - ||  -  || - 
| 212/87 || 45.7/64.4 || Wang et al. 2014
| Lin et al. 2015
|-
| TransR (unif)
| 232/219 || 78.3/91.7 || -  || - ||  -  || - 
| 226/78 || 43.8/65.5 || || Lin et al. 2015
|-
| TransR (bern)
| 238/225 || 79.8/92.0 || -  || - ||  -  || - 
| 198/77 || 48.2/68.7 || || Lin et al. 2015
|-
| CTransR (unif)
| 243/230 || 78.9/92.3 || -  || - ||  -  || - 
| 233/82 || 44/66.3 || || Lin et al. 2015
|-
| CTransR (bern)
| 231/218 || 79.4/92.3 || -  || - ||  -  || - 
| 199/75 || 48.4/70.2 || || Lin et al. 2015
|}

== Triple classification ==

{|class=wikitable
|-
| Data Sets || WN11 || FB13 || FB15K || Desc. Ref. || Perf. Ref.
|-
| SE || 53.0 || 75.2 || - || || Lin et al. 2015<ref name=lin15>Lin, Y., Liu, Z., Sun, M., Liu, Y., & Zhu, X. (2015). Learning Entity and Relation Embeddings for Knowledge Graph Completion. Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence Learning, 2181–2187.</ref>
|-
| SME (bilinear) || 70.0 || 63.7 || - || || Lin et al. 2015
|-
| SLM || 69.9 || 85.3 || - || || Lin et al. 2015
|-
| LFM || 73.8 || 84.3 || - || || Lin et al. (2015)
|-
| NTN || 70.4 || 87.1 || 68.5 || || Lin et al. (2015)
|-
| TransE (unif) || 75.9 || 70.9 || 79.6 || || Lin et al. (2015)
|-
| TransE (bern) || 75.9 || 81.5 || 79.2 || || Lin et al. (2015)
|-
| TransH (unif) || 77.7 || 76.5 || 79.0 || || Lin et al. (2015)
|-
| TransH (bern) || 78.8 || 83.3 || 80.2 || || Lin et al. (2015)
|-
| TransR (unif) || 85.5 || 74.7 || 81.7 || || Lin et al. (2015)
|-
| TransR (bern) || 85.9 || 82.5 || 83.9 || || Lin et al. (2015)
|-
| CTransR (bern)|| 85.7 || - || 84.5 || || Lin et al. (2015)
|-
| Bilinear COMP (initialized randomly) || 77.6 || 87.6 || - || || Guu et al. (2015)<ref>Guu, K., Miller, J., & Liang, P. (2015). Traversing knowledge graphs in vector space. Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing (EMNLP ’15), (September), 318–327.</ref>
|-
| Bilinear COMP (word vector) || 86.1 || 89.4 || - || || Guu et al. (2015)
|-
| TransE COMP (initialized randomly) || 80.3 || 84.9 || - || || Guu et al. (2015)
|-
| TransE COMP (word vector) || 87.6 || 89.6 || - || || Guu et al. (2015)
|}

== Notes ==

* Datasets:
** FB15K: Bordes et al. (2014)<ref>Bordes, A.; Glorot, X.;Weston, J.; and Bengio, Y. 2014. A semantic matching energy function for learning with multi- relational data. Machine Learning 94(2):233–259.</ref>
** FB13: Socher et al. (2013)<ref>Socher, R.; Chen, D.; Manning, C. D.; and Ng, A. 2013. Reasoning with neural tensor networks for knowledge base completion. In Proceedings of NIPS, 926–934.</ref>
* Numbers from Lin et al. (2015)<ref name=lin15></ref>: we have two number, first is "raw", second is "filter". As described in the paper: 
*: "a corrupted triple may also exist in knowledge graphs, which should be also considered as correct. However, the above evaluation may under-estimate those systems that rank these corrupted but correct triples high. Hence, before ranking we may filter out these corrupted triples which have appeared in knowledge graph. We name the first evaluation setting as “Raw” and the latter one as “Filter”."

== References ==
<references/>
[[Category:Knowledge base]]
[[Category:State of the art]]
@@ Line 1: / Line 1: @@
-TODO: neighborhood mixture model (Nguyen et al., 2016)<ref name=":0">Nguyen, D. Q., Sirts, K., Qu, L., & Johnson, M. (2016). Neighborhood Mixture Model for Knowledge Base Completion. Retrieved from http://arxiv.org/abs/1606.06461</ref>
 == Link (argument) prediction ==
@@ Line 128: / Line 127: @@
 | TransE COMP (word vector) || 87.6 || 89.6 || - || || Guu et al. (2015)
 |}
-== Relation prediction ==
-see Nguyen et al. (2016)<ref name=":0" />
 == Notes ==