A survey of Existing V&V, UQ and M&S Data and Knowledge Bases in Support of the Nuclear Energy - Knowledge base for Advanced Modeling and Simulation (NE-KAMS)

Xper3 (Vignes Lebbe et al. 2016) is a collaborative knowledge base publishing platform that, since its launch in november 2013, has been adopted by over 2 thousand users (Pinel et al. 2017). This is mainly due to its user friendly interface and the simplicity of its data model. The data are stored in MySQL Relational DBs, but the exchange format uses the TDWG standard format SDD (Structured Descriptive DataHagedorn et al. 2005). However, each Xper3 knowledge base is a closed world that the author(s) may or may not share with the scientific community or the public via publishing content and/or identification key (Kopfstein 2016). The explicit taxonomic, geographic and phenotypic limits of a knowledge base are not always well defined in the metadata fields. Conversely terminology vocabularies, such as Phenotype and Trait Ontology PATO and the Plant Ontology PO, and software to edit them, such as Protégé and Phenoscape, are essential in the semantic web, but difficult to handle for biologist without computer skills. These ontologies constitute open worlds, and are expressed themselves by RDF triples (Resource Description Framework). Protégé offers vizualisation and reasoning capabilities for these ontologies (Gennari et al. 2003, Musen 2015). Our challenge is to combine the user friendliness of Xper3 with the expressive power of OWL (Web Ontology Language), the W3C standard for building ontologies. We therefore focused on analyzing the representation of the same taxonomic contents under Xper3 and under different models in OWL. After this critical analysis, we chose a description model that allows automatic export of SDD to OWL and can be easily enriched. We will present the results obtained and their validation on two knowledge bases, one on parasitic crustaceans (Sacculina) and the second on current ferns and fossils (Corvez and Grand 2014). The evolution of the Xper3 platform and the perspectives offered by this link with semantic web standards will be discussed.

Download Full-text

Improving the Quality of Linked Data Using Statistical Distributions

Information Retrieval and Management ◽

10.4018/978-1-5225-5191-1.ch074 ◽

2018 ◽

pp. 1638-1664 ◽

Cited By ~ 1

Author(s):

Heiko Paulheim ◽

Christian Bizer

Keyword(s):

Knowledge Base ◽

Linked Data ◽

Relational Databases ◽

Knowledge Bases ◽

Structured Data ◽

Data Sources ◽

Data Sets ◽

Statistical Distributions ◽

The Web

Linked Data on the Web is either created from structured data sources (such as relational databases), from semi-structured sources (such as Wikipedia), or from unstructured sources (such as text). In the latter two cases, the generated Linked Data will likely be noisy and incomplete. In this paper, we present two algorithms that exploit statistical distributions of properties and types for enhancing the quality of incomplete and noisy Linked Data sets: SDType adds missing type statements, and SDValidate identifies faulty statements. Neither of the algorithms uses external knowledge, i.e., they operate only on the data itself. We evaluate the algorithms on the DBpedia and NELL knowledge bases, showing that they are both accurate as well as scalable. Both algorithms have been used for building the DBpedia 3.9 release: With SDType, 3.4 million missing type statements have been added, while using SDValidate, 13,000 erroneous RDF statements have been removed from the knowledge base.

Download Full-text

Formal Query Building with Query Structure Prediction for Complex Question Answering over Knowledge Base

Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2020/519 ◽

2020 ◽

Author(s):

Yongrui Chen ◽

Huiying Li ◽

Yuncheng Hua ◽

Guilin Qi

Keyword(s):

Knowledge Base ◽

Structure Prediction ◽

Question Answering ◽

State Transition ◽

Knowledge Bases ◽

Second Stage ◽

Transition Strategy ◽

Query Structure ◽

Two Stages ◽

Complex Question

Formal query building is an important part of complex question answering over knowledge bases. It aims to build correct executable queries for questions. Recent methods try to rank candidate queries generated by a state-transition strategy. However, this candidate generation strategy ignores the structure of queries, resulting in a considerable number of noisy queries. In this paper, we propose a new formal query building approach that consists of two stages. In the first stage, we predict the query structure of the question and leverage the structure to constrain the generation of the candidate queries. We propose a novel graph generation framework to handle the structure prediction task and design an encoder-decoder model to predict the argument of the predetermined operation in each generative step. In the second stage, we follow the previous methods to rank the candidate queries. The experimental results show that our formal query building approach outperforms existing methods on complex questions while staying competitive on simple questions.

Download Full-text

Nuclear Energy Advanced Modeling and Simulation (NEAMS) Accident Tolerant Fuels High Impact Problem: Coordinate Multiscale U3Si2 Modeling

10.2172/1376903 ◽

2017 ◽

Author(s):

K. A. Gamble ◽

J. D. Hales ◽

Y. Miao ◽

D. Andersson ◽

Y. Zhang

Keyword(s):

Modeling And Simulation ◽

Nuclear Energy ◽

High Impact ◽

Impact Problem

Download Full-text

Data mining for building knowledge bases: techniques, architectures and applications

The Knowledge Engineering Review ◽

10.1017/s0269888916000047 ◽

2016 ◽

Vol 31 (2) ◽

pp. 97-123 ◽

Cited By ~ 4

Author(s):

Alfred Krzywicki ◽

Wayne Wobcke ◽

Michael Bain ◽

John Calvo Martinez ◽

Paul Compton

Keyword(s):

Data Mining ◽

Knowledge Base ◽

Question Answering ◽

Knowledge Bases ◽

Event Extraction ◽

Data Sources ◽

Small Scale ◽

Knowledge Mining ◽

Practical Applications ◽

Unstructured Text

AbstractData mining techniques for extracting knowledge from text have been applied extensively to applications including question answering, document summarisation, event extraction and trend monitoring. However, current methods have mainly been tested on small-scale customised data sets for specific purposes. The availability of large volumes of data and high-velocity data streams (such as social media feeds) motivates the need to automatically extract knowledge from such data sources and to generalise existing approaches to more practical applications. Recently, several architectures have been proposed for what we callknowledge mining: integrating data mining for knowledge extraction from unstructured text (possibly making use of a knowledge base), and at the same time, consistently incorporating this new information into the knowledge base. After describing a number of existing knowledge mining systems, we review the state-of-the-art literature on both current text mining methods (emphasising stream mining) and techniques for the construction and maintenance of knowledge bases. In particular, we focus on mining entities and relations from unstructured text data sources, entity disambiguation, entity linking and question answering. We conclude by highlighting general trends in knowledge mining research and identifying problems that require further research to enable more extensive use of knowledge bases.

Download Full-text