AKSW - Projects/DLLearner/OnePageIntroduction

2009-05-12 11:47:15

Comparison for /Projects / DL Learner / One Page Introduction of 2009-05-12 11:47:15 and 2009-05-12 11:49:08

Additions:

Purposes of Class Expression Learning

Deletions:

Purposes of class learning

2009-05-12 11:45:55

Comparison for /Projects / DL Learner / One Page Introduction of 2009-05-12 11:45:55 and 2009-05-12 11:47:15

Additions:

Prot�g�: In a family ontology, a Prot�g� user wants to create a definition for the Concept 'Father'. He / She already asserted some instances to the class Father. Now, the DL-Learner Protege plugin presents the definition (in Manchester OWL syntax): Male and hasChild some Thing.

Deletions:

Prot�g�: In a family ontology, a Prot�g� user wants to create a definition for the Concept 'Father'. He already asserted some instances for the class Father. Now, the DL-Learner Protege plugin presents the definition (in Manchester OWL syntax): Male and hasChild some Thing.

2009-05-12 11:41:54

Comparison for /Projects / DL Learner / One Page Introduction of 2009-05-12 11:41:54 and 2009-05-12 11:45:55

Additions:

Implementation

It has different learning algorithms, which offer several parameters for fine-tuning. It can solve four closely related learning problems: learning based on positive and negative examples, positive only learning, and learning definitions and subclass relationships in ontologies.
It has different learning algorithms, which can learn even more efficiently, if parameters are tuned.

Deletions:

Application / Algorithms

It has different learning algorithms, which can learn even more efficiently, if parameters are tuned. It can solve four different problems: learning based on positive and negative instances, positives only and learning based on existing classes and learning of subclass relationships.

2009-05-12 11:32:49

Comparison for /Projects / DL Learner / One Page Introduction of 2009-05-12 11:32:49 and 2009-05-12 11:41:54

Additions:

Instance Classification: A user maintains a list of favorites. Based on these favorites, OWL Concepts are learned with DL-Learner and presented to the user in Natural Language. Such a concept could be all articles about proteins that are written by researchers from Germany (e.g. in Manchester syntax: Proteins and hasAuthor some (Person and hasLocation some Germany)). New articles, which fall in this category and are added to the knowledge base, are presented to the user automatically, like a customized RSS feed.
Prot�g�: In a family ontology, a Prot�g� user wants to create a definition for the Concept 'Father'. He already asserted some instances for the class Father. Now, the DL-Learner Protege plugin presents the definition (in Manchester OWL syntax): Male and hasChild some Thing.

Application / Algorithms

The application is written in Java. A user manual can be found here. Also there is an overview, a page about its architecture, and a feature list Features. DL-Learner is available as Open-Source at Sourceforge.
It has different learning algorithms, which can learn even more efficiently, if parameters are tuned. It can solve four different problems: learning based on positive and negative instances, positives only and learning based on existing classes and learning of subclass relationships.
As reasoning is heavily used by DL-Learners algorithms, special methods were introduced to increase performance:

Fast Instance Checker is a reasoning component, that is custom tailored for the needs of DL-Learner. After an initial reasoning step on the basis of Pellet, results are pre-calculated and cached. Besides the significant performance boost, the component can optionally apply a form of closed world reasoning, which allows to learn expressions like forall and max/min cardinality. It is an approximate reasoning method, where as usual rare cases of incomplete reasoning results are justified by a huge increase in performance.
DL-Learner can also provide class suggestions for very large knowledge bases, since it uses local fragment reasoning, i.e. only the relevant part (which is small) is used for learning new classes. This enables class learning in real time on knowledge bases like DBpedia. More information can be found here.

Deletions:

Instance Classification: A user maintains a list of favorites. Based on these favorites OWL Concepts are learned with DL-Learner and presented to the user in Natural Language. Such a concept could be all articles about proteins that are written by researchers from Germany (e.g. in Manchester syntax: Proteins and hasAuthor some (Person and hasLocation some Germany)). New articles, which fall in this category are added to the knowledge base, are presented to the user automatically, like a customized RSS feed.
Prot�g�: In a family ontology a Prot�g� user wants to create a definition for the Concept 'Father'. He selects 3 individuals, of which he knows that they adhere to the concept 'Father' and three individuals which are not fathers. As a possible suggestion DL-Learner presents the definition (in Manchester): Male and hasChild some Thing.

Application / Algortihms

The application is written in Java. A user manual can be found here. Also there is an overview, a page about its architecture, and a feature list Features. DL-Learner is available as Open-Source at Sourceforge
It has different learning algorithms, which can learn even more effectively, if parameters are tuned. It can solve four different problems: learning based on positive and negative instances, positives only and learning based on existing classes and learning of subclass relationships.
As reasoning is heavily used by DL-Learners algorithms special methods were introduced to increase performance:

Fast Instance Checker is a reasoning component, that is custom tailored for the needs of DL-Learner. After an initial reasoning step on the basis of Pellet, results are pre-calculated and cached. Besides the enormous performance boost, the component can optionally apply a form of closed world reasoning, which allows to learn expressions like forall and max/min cardinality. We have not took the effort to investigate formal proofs of correctness. An empirical evaluation showed however, that results are the same. Correctness becomes a minor issue in navigation/recommendation scenarios as it is more important to provide suggestion fast than be formally correct.
DL-Learner can also provide class suggestions for very large knowledge bases with unlimited size, since it uses local reasoning, i.e. only the relevant part (which is small) is used for learning new classes. this enables class learning in real time on knowledge bases like DBpedia. More information can be found here

2009-05-12 09:57:38

Comparison for /Projects / DL Learner / One Page Introduction of 2009-05-12 09:57:38 and 2009-05-12 11:32:49

Additions:

The DL-Learner software learns concepts in Description Logics (DLs) from examples. Equivalently, it can be used to learn classes in OWL ontologies from selected objects. It extends Inductive Logic Programming to Descriptions Logics and the Semantic Web. The goal of DL-Learner is to provide a DL/OWL based machine learning tool to solve supervised learning tasks and support knowledge engineers in constructing knowledge and learning about the data they created.

Learn Definitions for Classes: Based on existing instances of an OWL class, DL-Learner can make suggestions for class definitions to be included as an owl:equivalentClass or rdfs:subClassOf Axiom. As the algorithm is biased towards short and human readable definitions, a knowledge engineer can be supported when editing the TBox of an ontology (see Protege Plugin).
Find similar instances: DL-Learner's suggested class expressions can be used to find similar instances via retrieval (Concept definitions as search). Scalable methods allow the generation of recommendations on the fly, e.g. in a web scenario (see DBpedia Navigator – in experimental stage).

Deletions:

The DL-Learner software learns concepts in Description Logics (DLs) from examples. Equivalently, it can be used to learn classes in OWL ontologies from selected objects. It extends Inductive Logic Programming to Descriptions Logics and the Semantic Web. The goal of DL-Learner is to provide a DL/OWL based machine learning tool to solve supervised learnings tasks and support knowledge engineers in constructing knowledge and learning about the data they created.

Learn Definitions for Classes: Based on existing instances of an OWL class DL-Learner can make suggestions for class definitions to be included as an owl:equivalentClass Axiom. As the algortihm is biased towards short and human readable definitions, a knowledge engineer can be supported when editing the TBox of an ontology Protege Plugin
Find similar instances: DL-Learner's suggested class definitions can be used to find similar instances via retrieval (Concept definitions as search). Scalable methods allow the generation of recommendations on the fly, e.g. in a web scenario DBpedia Navigator

2009-05-11 11:41:23

Comparison for /Projects / DL Learner / One Page Introduction of 2009-05-11 11:41:23 and 2009-05-12 09:57:38

Additions:

It has different learning algorithms, which can learn even more effectively, if parameters are tuned. It can solve four different problems: learning based on positive and negative instances, positives only and learning based on existing classes and learning of subclass relationships.

Deletions:

It has different learning algorithms, which can learn even more effectively, if parameters are tuned.

2009-05-11 11:40:28

Comparison for /Projects / DL Learner / One Page Introduction of 2009-05-11 11:40:28 and 2009-05-11 11:41:23

Additions:

DL-Learner can also provide class suggestions for very large knowledge bases with unlimited size, since it uses local reasoning, i.e. only the relevant part (which is small) is used for learning new classes. this enables class learning in real time on knowledge bases like DBpedia. More information can be found here

Deletions:

DL-Learner can also provide class suggestions for very large knowledge bases with unlimited size, since it uses local reasoning, i.e. only the relevant part (which is small) is used for learning new classes. this enables class learning in real time on knowledge bases like DBpedia.

2009-05-11 11:38:57

Comparison for /Projects / DL Learner / One Page Introduction of 2009-05-11 11:38:57 and 2009-05-11 11:40:28

Additions:

Deletions:

The application is written in Java. A user manual can be found here. Also there is an overview of the architecture Overview, and a feature list Features. DL-Learner is available as Open-Source at Sourceforge

2009-05-11 11:38:35

Comparison for /Projects / DL Learner / One Page Introduction of 2009-05-11 11:38:35 and 2009-05-11 11:38:57

Additions:

Deletions:

The application is written in Java. A user manual can be found here). Also there is an overview of the architecture http://dl-learner.org/wiki/Overview Overview, and a feature list Features. DL-Learner is available as Open-Source at Sourceforge