Ontology-Driven Information Extraction with OntoSyphon

McDowell, Luke K.; Cafarella, Michael

doi:10.1007/11926078_31

Cited by 36 publications

(22 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Cimiano et al System [15] is a pattern-based approach to categorize instances with regard to ontology. OntoSyphon [16] uses the ontology to specify web searches that identify possible semantic instances, relations, and taxonomic information. The Maedche et al system [17] is bootstrapping approach that allows for the fast creation of an ontology-based information extracting system.…”

Section: Related Workmentioning

confidence: 99%

A Discovery Method of Anteroposterior Correlation for Big Data Era

Nakanishi

2015

Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing

View full text Add to dashboard Cite

Abstract. In this paper, we present a new knowledge extraction method on Big data era. We introduce new concepts, anteroposterior correlation, and propose an extraction method of anteroposterior correlation. The anteroposterior correlation means the correlation based on the time anteroposterior relation. We consider that Heterogeneity, continuity, and visualization are the most critical features of Big data analytics, which provides a scale and connection merits based on them. No current data analysis methods are based on opened assumptions. Big data analytics provides a new data analysis method based on opening assumptions. In this paper, we especially focus on an aspect of heterogeneity. We discover a correlation in consideration of the continuity of time. By our method, we effectively discover relationships between heterogeneous things, events and phenomena. The anteroposterior correlations are represented in relative comparison with each conditional probability distribution. The one of the features of our method is a measurement correlation by using conditional probability. That is, we calculate the correlation relative by representing all in conditional probability, no absolutely. Our method is determined higher correlation by comparison to each heterogeneous thing, event and phenomenon. This is the most important points on the Big data era. When you apply current association rule extraction techniques, you obtain too big rule base to organize them. By our method, we realize the one of the methods for decision mining.

show abstract

Section: Related Workmentioning

confidence: 99%

A Discovery Method of Anteroposterior Correlation for Big Data Era

Nakanishi

2015

Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing

View full text Add to dashboard Cite

show abstract

“…Many OBIE systems only extract instances for classes and property values for properties. Such OBIE systems include PANKOW [9], [10]), SOBA [11], OntoSyphon [12], Vulcain [13], and KIM [14]. The Kylin system [15] constructs an ontology based on the structure of Wikipedia infoboxes.…”

Section: Other Related Workmentioning

confidence: 99%

Learning to Refine an Automatically Extracted Knowledge Base Using Markov Logic

Jiang

Lowd

Dou

2012

2012 IEEE 12th International Conference on Data Mining

View full text Add to dashboard Cite

Abstract-A number of text mining and information extraction projects such as TextRunner and NELL seek to automatically build knowledge bases from the rapidly growing amount of information on the web. In order to scale to the size of the web, these projects often employ ad hoc heuristics to reason about uncertain and contradictory information rather than reasoning jointly about all candidate facts. In this paper, we present a Markov logic-based system for cleaning an extracted knowledge base. This allows a scalable system such as NELL to take advantage of joint probabilistic inference, or, conversely, allows Markov logic to be applied to a web scale problem. Our system uses only the ontological constraints and confidence values of the original system, along with humanlabeled data if available. The labeled data can be used to calibrate the confidence scores from the original system or learn the effectiveness of individual extraction patterns. To achieve scalability, we introduce a neighborhood grounding method that only instantiates the part of the network most relevant to the given query. This allows us to partition the knowledge cleaning task into tractable pieces that can be solved individually. In experiments on NELL's knowledge base, we evaluate several variants of our approach and find that they improve both F1 and area under the precision-recall curve.

show abstract

“…In document management, researchers have studied approaches to relate specific domain knowledge in the form of concepts, objects and relations to textual documents (McDowell and Cafarella 2006;Eriksson 2007) and based on such semantic documents, some projects have studied how to create support for information management in team workflows by using domain-specific document features (Franz et al 2007;Leifler and Eriksson 2009). …”

Section: Related Workmentioning

confidence: 99%

Message classification as a basis for studying command and control communications—an evaluation of machine learning approaches

Leifler

Eriksson

2011

J Intell Inf Syst

View full text Add to dashboard Cite

Specifically, we report the results from evaluating machine leaning with respect to two metrics of classification performance: (1) the precision of finding a known transition between two activities in a work process, and (2) the precision of classifying messages similarly to human researchers that search for critical episodes in a workflow.The results indicate that classification based on text only provides higher precision results with respect to both metrics when compared to other machine learning approaches, and that the precision of classifying messages using text-based classification in already classified datasets was approximately 50%. We present the implications that these results have for the design of support systems based on machine learning, and outline how to practically use text classification for analyzing team communications by demonstrating a specific prototype support tool for workflow analysis.

show abstract

Ontology-Driven Information Extraction with OntoSyphon

Cited by 36 publications

References 23 publications

A Discovery Method of Anteroposterior Correlation for Big Data Era

A Discovery Method of Anteroposterior Correlation for Big Data Era

Learning to Refine an Automatically Extracted Knowledge Base Using Markov Logic

Message classification as a basis for studying command and control communications—an evaluation of machine learning approaches

Contact Info

Product

Resources

About