HighlightSemantic Web

Linked data quality of DBpedia, Freebase, OpenCyc, Wikidata, and YAGO

A survey comparing the data quality criteria of five large knowledge graphs.

The paper compares the data quality of five large knowledge graphs: DBpedia, Freebase, OpenCyc, Wikidata, and YAGO. It provides a framework for analyzing and selecting the most suitable graph for a given setting. The authors propose data quality criteria to evaluate these graphs.

Based on: Linked data quality of DBpedia, Freebase, OpenCyc, Wikidata, and YAGO · Semantic Web

Highlightopenalex.org

Semantic Parsing via Staged Query Graph Generation: Question Answering with Knowledge Base

This paper presents a method for question answering with knowledge bases using staged query graph generation.

The authors propose a semantic parsing approach that generates query graphs in stages to answer questions based on a knowledge base. This method improves the accuracy of question answering by iteratively refining the query graph. The proposed approach is evaluated on several benchmarks and shows competitive results compared to state-of-the-art methods.

Based on: Semantic Parsing via Staged Query Graph Generation: Question Answering with Knowledge Base

HighlightarXiv (Cornell University)

Embedding Entities and Relations for Learning and Inference in Knowledge Bases

A survey on approaches to learning first-order logic rules over knowledge graphs.

This paper reviews state-of-the-art systems for learning first-order logic rules over knowledge graphs. It conducts a comparative analysis of various approaches, including ILP-based, statistical path generalisation, and neuro-symbolic methods. The authors highlight important application scenarios of rule learning in knowledge graph completion, fact checking, and other research areas.

Based on: Embedding Entities and Relations for Learning and Inference in Knowledge Bases · arXiv (Cornell University)

HighlightJournal of Artificial Intelligence Research

Text Relatedness Based on a Word Thesaurus

A paper proposing a measure of semantic relatedness between texts using word-to-word semantic links.

The authors present a new approach to measuring text relatedness based on implicit semantic links between words.,They introduce Omiotis, a measure that capitalizes on the semantic relatedness between individual words and extends it to text-to-text relatedness.,Experimental evaluation shows that this method outperforms lexicon-based methods in selected tasks.

Based on: Text Relatedness Based on a Word Thesaurus · Journal of Artificial Intelligence Research

HighlightJournal of Web Semantics

YAGO: A Large Ontology from Wikipedia and WordNet

A large ontology constructed from Wikipedia and WordNet.

YAGO is a large-scale ontology that integrates information from Wikipedia and WordNet.,It was developed by Fabian M. Suchanek, Gjergji Kasneci, and Gerhard Weikum in 2008.,The ontology covers a wide range of entities and relationships, making it a valuable resource for knowledge graph applications.

Based on: YAGO: A Large Ontology from Wikipedia and WordNet · Journal of Web Semantics