• Corpus ID: 13707239

OK Google, What Is Your Ontology? Or: Exploring Freebase Classification to Understand Google's Knowledge Graph

@article{Chah2018OKGW,
  title={OK Google, What Is Your Ontology? Or: Exploring Freebase Classification to Understand Google's Knowledge Graph},
  author={Niel Chah},
  journal={ArXiv},
  year={2018},
  volume={abs/1805.03885}
}
  • Niel Chah
  • Published 10 May 2018
  • Computer Science
  • ArXiv
This paper reconstructs the Freebase data dumps to understand the underlying ontology behind Google's semantic search feature. [] Key Result These findings will provide a glimpse into the proprietary blackbox Knowledge Graph and what is meant by Google's mission to "organize the world's information and make it universally accessible and useful".

Figures and Tables from this paper

A Synthesis Survey of Ontology Evaluation Tools, Applications and Methods to Propose a Novel Branch in Evaluating the Structure of Ontologies: Graph-Independent Approach

This paper attempts to propose a novel branch in structural analysis of ontology through analyzing current methods, which is called Graph-independent approach.

Structural Quality Metrics to Evaluate Knowledge Graphs

This work presents six structural quality metrics that can measure the quality of knowledge graphs and analyzes cross-domain knowledge graphs on the web as well as ’Raftel’, Naver’s integrated knowledge graph.

STRUCTURAL ANALYSIS OF SEMANTIC RELATIONS REGARDING INTEGRATION AND ASSOCIATION OF SEMANTIC NETWORK IN VOCBENCH AS AN AGRICULTURAL ONTOLOGY

  • M. AmirhosseiniJ. Salim
  • Computer Science
    International Journal of Engineering Technologies and Management Research
  • 2020
The research results reveal that the taxonomic relations cover a wide area in VocBench, and the overloading was not seen in the usage of non-taxonomic relations.

Modeling paths in knowledge graphs for context-aware prediction and explanation of facts

This work proposes the context path model, which uses paths that capture the context of a given triple and provides explanations for predictions and shows that most of the paths the model uses as explanation are meaningful and provide evidence for assessing the correctness of triples.

Using Compositional Embeddings for Fact Checking

The approach ESTHER searches for metapaths in compositional embedding spaces instead of the graph itself and can detect supplementary evidence for assertions being true that can be exploited by existing fact checking approaches.

Uncovering Hidden Semantics of Set Information in Knowledge Bases

Knowledge Graphs Effectiveness in Neural Machine Translation Improvement

Two embedding constraints are described that employ Entity Linking (EL)---assigning a unique identity to entities---to associate words in training sentences with those in the KG, and a monolingual embedding constraint that supports an enhanced semantic representation of the source words through access to relations between entities in a KG.

Application of Knowledge Graphs to Provide Side Information for Improved Recommendation Accuracy

This work presents a new generic recommendation systems framework, that integrates knowledge graphs into the recommendation pipeline, and supports different knowledge graph representation formats, and facilitates format conversion, merging and information extraction needed for training recommendation methods.

A Framework for Enhancing Deep Learning Based Recommender Systems with Knowledge Graphs

This work presents a new generic recommender systems framework, that integrates knowledge graphs into the recommendation pipeline, and describes its design and implementation, and shows how such a framework can be specialized, taking the domain of movies as an example.

Characterization of Objects in Indoor Spaces of Human Occupation Using Knowledge Graphs

A knowledge graph is proposed to describe the semantic relationships of objects present in an indoor space, such as a bedroom in a house, using the Grakn NoSQL database, which allows defining a knowledge graph schema of type entity-relation.

References

SHOWING 1-10 OF 14 REFERENCES

Ontology Development 101: A Guide to Creating Your First Ontology

An ontology defines a common vocabulary for researchers who need to share information in a domain that includes machine-interpretable definitions of basic concepts in the domain and relations among them.

Freebase: a collaboratively created graph database for structuring human knowledge

MQL provides an easy-to-use object-oriented interface to the tuple data in Freebase and is designed to facilitate the creation of collaborative, Web-based data-oriented applications.

A Critical Analysis of Floridi’s Theory of Semantic Information

This work will defend the view that notions that are associated with truth, knowledge, and meaning all can adequately be reconstructed in the context of modern information theory and that consequently there is no need to introduce a concept of semantic information.

Sorting Things Out: Classification and Its Consequences

The authors present fascinating history and insights into the development of various classification systems and identify issues that arise during the creation of any classification system, such as the need to compromise between providing granular classifications that satisfy needs specific to a time and place.

Précis of Knowledge and the Flow of Information

Abstract A theory of information is developed in which the informational content of a signal (structure, event) can be specified. This content is expressed by a sentence describing the condition at a

Information as thing

Three meanings of “information” are distinguished: “Information‐as‐process”; “information‐as‐knowledge”; and “information‐as‐thing,” the attributive use of “information” to denote things regarded as

THE ANALYTICAL LANGUAGE OF JOHN WILKINS

I have noticed that the 14th edition of Encyclopedia Britannica does not include the article on John Wilkins. This omission can be considered justified if we remember how trivial this article was (20

The Mathematical Theory of Information

The Mathematical Theory of Information presents a new mathematical theory of information, built on a single powerful postulate: the Law of Diminishing Information, which is applied to information technology, game theory, legislation, logic of research, algorithmic information, chaos theory, control engineering, medical tests, and biological evolution.

So Long, and Thanks for All the …