Linked hypernyms: Enriching DBpedia with Targeted Hypernym Discovery

Kliegr, Tomáš

doi:10.1016/j.websem.2014.11.001

Cited by 30 publications

(29 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This algorithm bears some resemblance to the STI algorithm that we proposed in [5] (also covered in Section 5), since both algorithms exploit the occurrence of types. The association rule approach is more advanced in that if the entity has multiple types, all of them can potentially contribute to the type prediction.…”

Section: Unsupervised Methodsmentioning

confidence: 99%

“…The accuracy of LHD matches the results for Tipalo algorithm -as reported by its authors in [7] -for the type selection subtask (0.93 precision and 0.90 recall). A detailed comparison between LHD and Tipalo is presented in [2] as well as a more extensive literature review on pattern-based extraction.…”

Section: Pattern-based Analysis Of Unstructured Contentmentioning

confidence: 99%

“…Parts of the work presented in this article have been published within the conference paper "Towards Linked Hypernyms Dataset 2.0: complementing DBpedia with hypernym discovery and statistical type inference (Kliegr and Zamazal, 2014)" [5]. This article extends the conference paper by introducing the hierarchical SVM approach and by performing extensive evaluation on the contributed gold standard dataset allowing the community to track progress in accuracy and coverage of entity typing and extraction tools.…”

Section: Introductionmentioning

confidence: 98%

“…Our previously published Linked Hypernyms Dataset (LHD) framework [2] extracts types from the first sentence of Wikipedia articles using lexicosyntactic patterns. In this work we extend it with Statistical Type Inference (STI) which helps to map LHD results to the DBpedia Ontology used by the native DBpedia solution.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

LHD 2.0: A text mining approach to typing entities in knowledge graphs

Kliegr

Zamazal

2016

Journal of Web Semantics

Self Cite

View full text Add to dashboard Cite

The type of the entity being described is one of the key pieces of information in linked data knowledge graphs. In this article, we introduce a novel technique for type inference that extracts types from the free text description of the entity combining lexico-syntactic pattern analysis with supervised classification. For lexicosyntactic (Hearst) pattern-based extraction we use our previously published Linked Hypernyms Dataset Framework. Its output is mapped to the DBpedia Ontology with exact string matching complemented with a novel co-occurrence-based algorithm STI. This algorithm maps classes appearing in one knowledge graph to a different set of classes appearing in another knowledge graph provided that the two graphs contain common set of typed instances. The supervised results are obtained from a hierarchy of Support Vector Machines classifiers (hSVM) trained on the bag-of-words representation of short abstracts and categories of Wikipedia articles. The results of both approaches are probabilistically fused. For evaluation we created a gold-standard dataset covering over 2,000 DBpedia entities using a commercial crowdsourcing service. The hierarchical precision of our hSVM and STI approaches is comparable to SDType, the current state-of-theart type inference algorithm, while the set of applicable instances is largely complementary to SDType as our algorithms do not require semantic properties in the knowledge graph to type an instance. The paper also provides a comprehensive evaluation of type assignment in DBpedia in terms of hierarchical precision, recall and exact match with the gold standard. Dataset generated by a version of the presented approach is included in DBpedia 2015.

show abstract

Section: Unsupervised Methodsmentioning

confidence: 99%

Section: Pattern-based Analysis Of Unstructured Contentmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 98%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

LHD 2.0: A text mining approach to typing entities in knowledge graphs

Kliegr

Zamazal

2016

Journal of Web Semantics

Self Cite

View full text Add to dashboard Cite

show abstract

“…Identifying these invalid types and entities manually is unfeasible. In fact, the automatic enrichment and update of DBpedia with new type statements (through rdf:type) is becoming an important challenge [23,24]. In this paper, we rely on vector-based representations such as word embeddings and entity embeddings [25,26] to reach these objectives.…”

Section: Introductionmentioning

confidence: 99%

A Comparison of Word Embeddings and N-gram Models for DBpedia Type and Invalid Entity Detection

2018

View full text Add to dashboard Cite

This article presents and evaluates a method for the detection of DBpedia types and entities that can be used for knowledge base completion and maintenance. This method compares entity embeddings with traditional N-gram models coupled with clustering and classification. We tackle two challenges: (a) the detection of entity types, which can be used to detect invalid DBpedia types and assign DBpedia types for type-less entities; and (b) the detection of invalid entities in the resource description of a DBpedia entity. Our results show that entity embeddings outperform n-gram models for type and entity detection and can contribute to the improvement of DBpedia’s quality, maintenance, and evolution.

show abstract

A review of reasoning characteristics of RDF‐based Semantic Web systems

Colucci,

Donini,

Di Sciascio

2024

WIREs Data Min & Knowl

View full text Add to dashboard Cite

Presented as a research challenge in 2001, the Semantic Web (SW) is now a mature technology, used in several cross‐domain applications. One of its key benefits is a formal semantics of its RDF data format, which enables a system to validate data, infer implicit knowledge by automated reasoning, and explain it to a user; yet the analysis presented here of 71 RDF‐based SW systems (out of which 17 reasoners) reveals that the exploitation of such semantics varies a lot among all SW applications. Since the simple enumeration of systems, each one with its characteristics, might result in a clueless listing, we borrow from Software Engineering the idea of maturity model, and organize our classification around it. Our model has three orthogonal dimensions: treatment of blank nodes, degree of deductive capabilities, and explanation of results. For each dimension, we define 3–4 levels of increasing exploitation of semantics, corresponding to an increasingly sophisticated output in that dimension. Each system is then classified in each dimension, based on its documentation and published articles. The distribution of systems along each dimension is depicted in the graphical abstract. We deliberately exclude resources consumption (time and space) since it is a dimension not peculiar to SW.This article is categorized under: Fundamental Concepts of Data and Knowledge > Knowledge Representation Fundamental Concepts of Data and Knowledge > Explainable AI

show abstract

Linked hypernyms: Enriching DBpedia with Targeted Hypernym Discovery

Cited by 30 publications

References 7 publications

LHD 2.0: A text mining approach to typing entities in knowledge graphs

LHD 2.0: A text mining approach to typing entities in knowledge graphs

A Comparison of Word Embeddings and N-gram Models for DBpedia Type and Invalid Entity Detection

A review of reasoning characteristics of RDF‐based Semantic Web systems

Contact Info

Product

Resources

About