HighlightCurated by Aramai Editorial

Multilingual Knowledge Graph Embeddings for Cross-lingual Knowledge Alignment

A translation-based model for multilingual knowledge graph embeddings.

The paper proposes MTransE, a model that provides transitions for each embedding vector to its cross-lingual counterparts in other spaces. It can be trained on partially aligned graphs and preserves the key properties of monolingual embeddings. The experiments show promising results on cross-lingual entity matching and triple-wise alignment verification.

Based on: Multilingual Knowledge Graph Embeddings for Cross-lingual Knowledge Alignment

HighlightCurated by Aramai Editorial

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

HighlightCurated by Aramai Editorial

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

HighlightCurated by Aramai Editorial

HermiT: An OWL 2 Reasoner

A reasoner for the OWL 2 ontology language.

HermiT is a reasoner designed to support the OWL 2 ontology language, which is used for representing knowledge on the web.,The paper presents HermiT's architecture and its ability to perform reasoning tasks such as subsumption and satisfiability checking.,It also discusses the system's performance and scalability.

Based on: HermiT: An OWL 2 Reasoner · Journal of Automated Reasoning

HighlightCurated by Aramai Editorial

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)

HighlightCurated by Aramai Editorial

Semantic Parsing on Freebase from Question-Answer Pairs

A paper proposing a semantic parser that learns from question-answer pairs to scale up to Freebase.

The authors present a method for training a semantic parser using question-answer pairs, which outperforms previous state-of-the-art parsers. They tackle the challenge of narrowing down possible logical predicates by building a coarse mapping and using bridging operations. The paper also introduces a new dataset of question-answer pairs.

Based on: Semantic Parsing on Freebase from Question-Answer Pairs

HighlightCurated by Aramai Editorial

Weak signal identification with semantic web mining

This paper proposes a method for identifying weak signals using semantic web mining.

The authors present a framework that leverages semantic web technologies to identify weak signals in large datasets. They describe the application of this approach to a specific use case and evaluate its performance. The method is based on the idea of representing data as a graph and applying semantic reasoning techniques to extract relevant information.

Based on: Weak signal identification with semantic web mining · Expert Systems with Applications

HighlightCurated by Aramai Editorial

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

HighlightCurated by Aramai Editorial

OWL 2: The next step for OWL

A paper discussing the development and features of OWL 2.

The authors present an overview of OWL 2, a new version of the Web Ontology Language. They discuss its key features, including improved expressiveness and better support for reasoning. The paper also highlights the benefits of using OWL 2 in various applications.

Based on: OWL 2: The next step for OWL · Journal of Web Semantics

HighlightCurated by Aramai Editorial

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

HighlightCurated by Aramai Editorial

Handbook of Knowledge Representation

A handbook on knowledge representation, published in the Foundations of artificial intelligence series.

The Handbook of Knowledge Representation is a comprehensive resource covering various aspects of knowledge representation.,It provides an overview of the field, discussing topics such as formalisms and their applications.,The book is part of the Foundations of Artificial Intelligence series.

Based on: Handbook of Knowledge Representation · Foundations of artificial intelligence

HighlightCurated by Aramai Editorial

Ontological foundations for structural conceptual models

A thesis proposing ontological foundations for structural conceptual models.

The thesis contributes to Conceptual Modeling theory by introducing an evaluation method and a foundational ontology for general conceptual modeling languages. It proposes a systematic comparison of metamodels with reference ontologies, focusing on structural aspects. The developed ontology is used to create methodological tools and demonstrates applicability in extending the Unified Modeling Language (UML).

Based on: Ontological foundations for structural conceptual models · University of Twente Research Information