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

Abstract

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.

Mining knowledge graphs to map heterogeneous relations between the internet of things patterns

“…In other words, the ontological and semantic rules are grounded by substituting literals into formulas. Simply put, each ground rule consists of a weighted satisfaction metric derived from the formula's truth value which assigns a joint probability for each possible knowledge graph as in (12).…”

“…Knowledge graph databases provide an effective solution to support the task of storing related IoT patterns. At the moment, several models and architectures are being tested for their capabilities to mine knowledge graphs from text [12], [13]. This usually involves using a hybrid of natural language processing (NLP) techniques to extract important information from large corpora of text [14].…”

Embedding based Link Prediction for Knowledge Graph Completion

“…Another study [14] performs RDF type prediction in KGs with the help of the hierarchical SLCN algorithm using a set of incoming and outgoing relations as features for classification. In [13], the authors propose a supervised hierarchical SVM classification approach for DBpedia by exploiting the abstract and the categories of the Wikipedia articles. An embedding based model is proposed for entity typing [11] considering the structural information in the KG as well as the textual entity descriptions.…”

Semantic Web and Human Computation: The status of an emerging field

“…Potoniec et al propose an algorithm that extracts SubClassOf axioms from Linked Data sources and verify the correctness of the extracted axioms through crowdsourcing [35]. Kliegr et al evaluate their entity typing algorithm on a crowdsourced gold-standard data set of 2000 entities aligned with their corresponding types from the DBpedia ontology [25]. Note that here we only report on papers that made it clear already in their abstract that crowdsourcing is used for evaluation purposes, but we expect that this category of papers is much larger as it includes also papers that do not mention their evaluation approach in their abstract and were therefore not retrieved by our keyword-based search approach.…”