Knowledge Base Completion: Baselines Strike Back

Kadlec, Rudolf; Bajgar, Ondřej; Kleindienst, Jan

doi:10.48550/arxiv.1705.10744

Cited by 19 publications

(37 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Results of several models evaluated on the FB15K and WN18 datasets. Results of [♥] are taken from(Nickel et al, 2016) and results of [♦] are taken from(Kadlec et al, 2017). Other results are taken from the corresponding original papers.…”

mentioning

confidence: 99%

RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space

Sun,

Deng,

Nie

et al. 2019

Preprint

180

384

View full text Add to dashboard Cite

We study the problem of learning representations of entities and relations in knowledge graphs for predicting missing links. The success of such a task heavily relies on the ability of modeling and inferring the patterns of (or between) the relations. In this paper, we present a new approach for knowledge graph embedding called RotatE, which is able to model and infer various relation patterns including: symmetry/antisymmetry, inversion, and composition. Specifically, the RotatE model defines each relation as a rotation from the source entity to the target entity in the complex vector space. In addition, we propose a novel self-adversarial negative sampling technique for efficiently and effectively training the RotatE model. Experimental results on multiple benchmark knowledge graphs show that the proposed RotatE model is not only scalable, but also able to infer and model various relation patterns and significantly outperform existing state-of-the-art models for link prediction.

show abstract

mentioning

confidence: 99%

RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space

Sun,

Deng,

Nie

et al. 2019

Preprint

180

384

View full text Add to dashboard Cite

show abstract

“…KG completion: there are many models that have been used for KG completion. Among those models, Complex Embeddings (ComplEx) [62] has achieved promising results in comparison to other methods [63,64]. ComplEx is considered the simplification of DistMult [65].…”

Section: Kg Error Correctionmentioning

confidence: 99%

An Automatic Ontology Generation Framework with An Organizational Perspective

Elnagar

Yoon

Thomas

2020

Proceedings of the Annual Hawaii International Conference on System Sciences

View full text Add to dashboard Cite

Ontologies have been known for their powerful semantic representation of knowledge. However, ontologies cannot automatically evolve to reflect updates that occur in respective domains. To address this limitation, researchers have called for automatic ontology generation from unstructured text corpus. Unfortunately, systems that aim to generate ontologies from unstructured text corpus are domain-specific and require manual intervention. In addition, they suffer from uncertainty in creating concept linkages and difficulty in finding axioms for the same concept. Knowledge Graphs (KGs) has emerged as a powerful model for the dynamic representation of knowledge. However, KGs have many quality limitations and need extensive refinement. This research aims to develop a novel domain-independent automatic ontology generation framework that converts unstructured text corpus into domain consistent ontological form. The framework generates KGs from unstructured text corpus as well as refine and correct them to be consistent with domain ontologies. The power of the proposed automatically generated ontology is that it integrates the dynamic features of KGs and the quality features of ontologies.

show abstract

“…TransH (Wang et al, 2014), TransR (Lin et al, 2015), TransD (Ji et al, 2015), and ITransF (Xie et al, 2017) are the extensions of TransE, which introduce other parameters to map the entities and relations to different semantic spaces. The Single DistMult (Kadlec et al, 2017) increases the embedding size of the Dist-Mult to obtain more expressive features. Besides, ProjE (Shi and Weninger, 2017), ConvE (Dettmers et al, 2018) and InteractE (Vashishth et al, 2019) leverage neural networks to capture more feature interactions between embeddings and thus improves the expressiveness.…”

Section: Related Workmentioning

confidence: 99%

“…TransE (Bordes et al, 2013) ||h + r − t|| Low Small DistMult h, r, t Low Small ComplEx (Trouillon et al, 2016) Re( h, r, t ) Low Small Single DistMult (Kadlec et al, 2017) h, r, t High Large ConvE (Dettmers et al, 2018) f (vec(f([h, r] * ω))W)t High Large SEEK sx,y rx, hy, tw x,y High Small…”

Section: Sym Antisymmentioning

confidence: 99%

“…In contrast, the second category pursues the excellent expressiveness but introduces much more model parameters and tensor computations. Typical examples include TransH (Wang et al, 2014), TransR (Lin et al, 2015), TransD (Ji et al, 2015), Single DistMult (Kadlec et al, 2017), ConvE (Dettmers et al, 2018) and Inter-actE (Vashishth et al, 2019). However, as pointed out by Dettmers et al (2018), the high model complexity often leads to poor scalability, which is prohibitive in practice because real-world KGs usually contain massive triples.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

SEEK: Segmented Embedding of Knowledge Graphs

Zheng

et al. 2020

Preprint

View full text Add to dashboard Cite

In recent years, knowledge graph embedding becomes a pretty hot research topic of artificial intelligence and plays increasingly vital roles in various downstream applications, such as recommendation and question answering. However, existing methods for knowledge graph embedding can not make a proper trade-off between the model complexity and the model expressiveness, which makes them still far from satisfactory. To mitigate this problem, we propose a lightweight modeling framework that can achieve highly competitive relational expressiveness without increasing the model complexity. Our framework focuses on the design of scoring functions and highlights two critical characteristics: 1) facilitating sufficient feature interactions; 2) preserving both symmetry and antisymmetry properties of relations. It is noteworthy that owing to the general and elegant design of scoring functions, our framework can incorporate many famous existing methods as special cases. Moreover, extensive experiments on public benchmarks demonstrate the efficiency and effectiveness of our framework. Source codes and data can be found at https://github.com/ Wentao-Xu/SEEK.

show abstract

Knowledge Base Completion: Baselines Strike Back

Cited by 19 publications

References 0 publications

RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space

RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space

An Automatic Ontology Generation Framework with An Organizational Perspective

SEEK: Segmented Embedding of Knowledge Graphs

Contact Info

Product

Resources

About