Querying Factorized Probabilistic Triple Databases

Krompaβ, Denis; Nickel, Maximilian; Tresp, Volker

doi:10.1007/978-3-319-11915-1_8

Cited by 19 publications

(16 citation statements)

References 24 publications

(16 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Given the current model and a set of newly observed relationships, latent representations of new entities can be calculated approximately in both tensor factorization models and in neural networks, by finding representations that explain the newly observed relationships relative to the current model. Similarly, it has been shown that the relation-specific weights W k in the RESCAL model can be calculated efficiently for new relation types given already derived latent representations of entities [140].…”

Section: Generalizing To New Entities and Relationsmentioning

confidence: 99%

A Review of Relational Machine Learning for Knowledge Graphs

et al. 2016

Self Cite

View full text Add to dashboard Cite

Relational machine learning studies methods for the statistical analysis of relational, or graph-structured, data. In this paper, we provide a review of how such statistical models can be "trained" on large knowledge graphs, and then used to predict new facts about the world (which is equivalent to predicting new edges in the graph). In particular, we discuss two fundamentally different kinds of statistical relational models, both of which can scale to massive datasets. The first is based on latent feature models such as tensor factorization and multiway neural networks. The second is based on mining observable patterns in the graph. We also show how to combine these latent and observable models to get improved modeling power at decreased computational cost. Finally, we discuss how such statistical models of graphs can be combined with text-based information extraction methods for automatically constructing knowledge graphs from the Web. To this end, we also discuss Google's Knowledge Vault project as an example of such combination.Comment: To appear in Proceedings of the IEE

show abstract

Section: Generalizing To New Entities and Relationsmentioning

confidence: 99%

A Review of Relational Machine Learning for Knowledge Graphs

et al. 2016

Self Cite

View full text Add to dashboard Cite

show abstract

“…implementation achieved very similar results to the original model on a smaller dataset 11 (results not shown).…”

Section: Implementation and Model Training Detailsmentioning

confidence: 60%

“…Latent variable models have recently been exploited for generating priors for facts in the context of automatic graph-based knowledge-base construction [8]. It has also been shown that these models can be interpreted as a compressed probabilistic knowledge representation, which allows complex querying over all possible triples and their uncertainties, resulting in a probabilistically ranked list of query answers [11].…”

Section: Introductionmentioning

confidence: 99%

Type-Constrained Representation Learning in Knowledge Graphs

Krompaβ

Baier

Tresp

2015

Lecture Notes in Computer Science

Self Cite

163

127

View full text Add to dashboard Cite

Abstract. Large knowledge graphs increasingly add value to various applications that require machines to recognize and understand queries and their semantics, as in search or question answering systems. Latent variable models have increasingly gained attention for the statistical modeling of knowledge graphs, showing promising results in tasks related to knowledge graph completion and cleaning. Besides storing facts about the world, schema-based knowledge graphs are backed by rich semantic descriptions of entities and relation-types that allow machines to understand the notion of things and their semantic relationships. In this work, we study how type-constraints can generally support the statistical modeling with latent variable models. More precisely, we integrated prior knowledge in form of type-constraints in various state of the art latent variable approaches. Our experimental results show that prior knowledge on relation-types significantly improves these models up to 77% in linkprediction tasks. The achieved improvements are especially prominent when a low model complexity is enforced, a crucial requirement when these models are applied to very large datasets. Unfortunately, typeconstraints are neither always available nor always complete e.g., they can become fuzzy when entities lack proper typing. We show that in these cases, it can be beneficial to apply a local closed-world assumption that approximates the semantics of relation-types based on observations made in the data.

show abstract

“…Such models learn lowdimensional distributed representations-also referred to as embeddings-of all entities and relations in a knowledge graph. Neural link predictors are currently the state of the art approach to tasks such as link prediction [4,8,35,39], entity disambiguation and entity resolution [3], taxonomy extraction [25,29], and probabilistic question answering [17].…”

Section: Triples Probabilitymentioning

confidence: 99%

Embedding cardinality constraints in neural link predictors

Muñoz

Minervini

Nickles

2019

Proceedings of the 34th ACM/SIGAPP Symposium on Applied Computing

View full text Add to dashboard Cite

Neural link predictors learn distributed representations of entities and relations in a knowledge graph. They are remarkably powerful in the link prediction and knowledge base completion tasks, mainly due to the learned representations that capture important statistical dependencies in the data. Recent works in the area have focused on either designing new scoring functions or incorporating extra information into the learning process to improve the representations. Yet the representations are mostly learned from the observed links between entities, ignoring commonsense or schema knowledge associated to the relations in the graph. A fundamental aspect of the topology of relational data is the cardinality information, which bounds the number of predictions given for a relation between a minimum and maximum frequency. In this paper, we propose a new regularisation approach to incorporate relation cardinality constraints to any existing neural link predictor without affecting their efficiency or scalability. Our regularisation term aims to impose boundaries on the number of predictions with high probability, thus, structuring the embeddings space to respect commonsense cardinality assumptions resulting in better representations. Experimental results on Freebase, WordNet and YAGO show that, given suitable prior knowledge, the proposed method positively impacts the predictive accuracy of downstream link prediction tasks.

show abstract

Querying Factorized Probabilistic Triple Databases

Cited by 19 publications

References 24 publications

A Review of Relational Machine Learning for Knowledge Graphs

A Review of Relational Machine Learning for Knowledge Graphs

Type-Constrained Representation Learning in Knowledge Graphs

Embedding cardinality constraints in neural link predictors

Contact Info

Product

Resources

About