Thomas Roth-berghofer | University of West London (original) (raw)

Papers by Thomas Roth-berghofer

MedCIRCLE (www.medcircle.info) is a semantic web project to develop and promote technologies able... more MedCIRCLE (www.medcircle.info) is a semantic web project to develop and promote technologies able to guide consumers to trustworthy health information on the Internet and to establish a global web of trust for networked health information. Gateway sites for consumer health information (CisMEF, AQU-MED, Certified Medical Web Site Seal ofMETGES online) will use HIDDEL metadata (Health Information Disclosure, Description and Evaluation Language, expressed in XMI/RDF Syntax) to make their annotation and evaluation data machineprocessable and accessible for software-agents. Other health subject gateways, accreditation, or rating services are invited to join the collaboration by implementing HIDDEL on their gateways. Expressing self-descriptive or third-party evaluations a machine-processableformat allows intelligent agents or client-side software to harvest statements and opinions about the trustworthiness ofother websites and assist users in selecting trustworthy websites. The MedCIRCLE project builds on, expands and continues work on rating health information on the Internet piloted within the MedCERTAIN project. While MedCERTAINprovided the core technologies and software for rating and "trustmarking" health tnformation, MedCIRCLE is built around these technologies and involves a wider medical community to assess health information, demonstrating the power of collaborative and interoperable evaluations on the world-wide-web. Other specific aims include refinement and expansion of HIDDEL, to become a standard vocabulary and interchange format for selfand third-party ratings of health information.

Explanation-aware Computing, 2009

... Semantic Web and Web 2.0. M Greaves, P Mika in Web Semantics Science Services and Agents on t... more ... Semantic Web and Web 2.0. M Greaves, P Mika in Web Semantics Science Services and Agents on the World Wide Web (2008). 2 readers Save reference to library · Related research.Semantic Web or Web 2.0? Socialization of the Semantic Web. ...

... VIII Organization Program Committee Agnar Aamodt, Norwegian University of Science and Technol... more ... VIII Organization Program Committee Agnar Aamodt, Norwegian University of Science and Technology, Norway Varol Akman, Bilkent University, Turkey Elena Andonova, New Bulgarian University, Bulgaria Nicholas Asher, IRIT, France, and University of Texas, USA John ...

Teaching machines to understand human communication is one of the central goals of artificial int... more Teaching machines to understand human communication is one of the central goals of artificial intelligence. Psychological research indicates that human associations are an essential requirement to understand human communication. In this paper the hypothesis is presented that simulating human associations with the help of Linked Data could improve text understanding capabilities of machines. To investigate whether human associations can be simulated with Linked Data, two preliminary problems are identified: (i) A reasonable ground truth for human associations is lacking and (ii) human associations have different strengths while Linked Data treats all triples equally and does not provide edge weights. To overcome these problems, two ideas for web games in accordance with Luis von Ahn's Games with a Purpose are proposed trying to turn the tedious acquisition processes into fun games. The resulting datasets are then to be used for quantitative comparisons of human associations and Linked Data.

Research on explanation in Case-Based Reasoning (CBR) is a topic that gains momentum. In this con... more Research on explanation in Case-Based Reasoning (CBR) is a topic that gains momentum. In this context, fundamental issues on what are and to which end do we use explanations have to be reconsidered. This article presents a prelimenary outline of the combination of two recently proposed classifications of explanations based on the type of the explanation itself and user goals which should be fulfilled.

The information extraction system iDocument interactively extracts information from texts such as... more The information extraction system iDocument interactively extracts information from texts such as instances and relations with respect to existing background knowledge. An extraction process creates weighted hypotheses describing indications of relevant information. During execution, each process step records its output into an instantiated process model. We reused these bits of information for generating conceptual, functional as well as causal explanations. In order to visualise explanations, our component utilises different mechanisms for textual, explorative, and pictorial rendering styles.

... Maguitman (Indiana University, USA) Heiko Maus (DFKI GmbH, Kaiserslautern, Germany) Enrico Ru... more ... Maguitman (Indiana University, USA) Heiko Maus (DFKI GmbH, Kaiserslautern, Germany) Enrico Rukzio (University of Munich, Germany) Thomas Strang (DLR, Germany) Page 9. Table of Contents Using Activity Theory to Model Context Awareness Anders Kofod-Petersen, Jorg ...

The information extraction system iDocument interactively extracts information from text such as ... more The information extraction system iDocument interactively extracts information from text such as instances and relations with respect to existing background knowledge. An extraction process creates weighted recommendations describing indications of relevant information. During execution, each process step records its output into an instantiated process model. We reused these bits of information for generating conceptual, functional as well as causal explanations. The purpose of these explanations is to illustrate the evolution of recommendations for convincing users of their validity. In order to visualise explanations, our component utilises different mechanisms for textual, tabular, and graphical rendering styles.

Lecture Notes in Computer Science, 2005

Having people from two sciences come together appears to be a difficult task, especially when one... more Having people from two sciences come together appears to be a difficult task, especially when one of the sciences has a tradition that can be counted in millennia and where the other one some decades ago simply did not exist. Todays talking about ontologies in informatics (computer science), for instance, can easily be misleading. The term is borrowed from philosophy

KI - Künstliche Intelligenz, 2014

ABSTRACT This paper describes an approach to externalising and formalising expert knowledge invol... more ABSTRACT This paper describes an approach to externalising and formalising expert knowledge involved in the design and evaluation of hydrometallurgical process chains for gold ore treatment. The objective was to create a case-based reasoning application for recommending and validating a treatment process of gold ores. We describe a twofold approach. Formalising human expert knowledge about gold mining situations enables the retrieval of similar mining contexts and respective process chains, based on prospection data gathered from a potential gold mining site. Secondly, empirical knowledge on hydrometallurgical treatments is formalised. This enabled us to evaluate and, where needed, redesign the process chain that was recommended by the first aspect of our approach. The main problems with formalisation of knowledge in the domain of gold ore refinement are the diversity and the amount of parameters used in literature and by experts to describe a mining context. We demonstrate how similarity knowledge was used to formalise literature knowledge. The evaluation of data gathered from experiments with an initial prototype workflow recommender, Auric Adviser, provides promising results.

Proceedings of the 21st international conference companion on World Wide Web - WWW '12 Companion, 2012

In this paper we describe the task of automated mining for solutions to highly specific problems.... more In this paper we describe the task of automated mining for solutions to highly specific problems. We do so under the premise of mapping the split view on context, introduced by Brézillon and Pomerol, onto three different levels of abstraction of a problem domain. This is done to integrate the notion of activity or focus and its influence on the context into the mining for a solution. We assume that a problem's context describes key characteristics to be decisive criteria in the mining process to mine successful solutions for it. We further detail on the process of a chain of sub problems and their foci adding up to a meta problem solution and how this can used to mine for such solutions. Through a guiding example we introduce basic steps of the solution mining process and common aspects we deem interesting to be analysed closer in upcoming research on solution mining. We further examine the possible integration of these newly established outlines for automatic solution mining for highly specific problems into a Seasalt exp , a currently developed architecture for explanation-aware extraction and case-based processing of experiences from Internet communities. We thereby gained first insights in issues occurring while trying to integrate automatic solution mining.

Lecture Notes in Computer Science, 2012

The role of maintenance in the domain of case-based reasoning sys- tems is extremely important. T... more The role of maintenance in the domain of case-based reasoning sys- tems is extremely important. Therefore, methods of maintaining case bases using case properties will be presented. Definitions of the case properties (correctness, consistency, incoherence, minimality, and uniqueness) are given. The use of these properties in five experiments is explained, and the results of these experiments on nine real world

ConTag is an approach to generate semantic tag recommendations for doc- uments based on Semantic ... more ConTag is an approach to generate semantic tag recommendations for doc- uments based on Semantic Web ontologies and Web 2.0 services. We designed and im- plemented a process to normalize documents to RDF format, extract document topics using Web 2.0 services and finally match extracted topics to a Semantic Web ontology. Due to ConTag we are able to show that

This paper describes an approach to externalising and formalising expert knowledge involved in th... more This paper describes an approach to externalising and formalising expert knowledge involved in the design and evaluation of hydrometallurgical process chains for gold ore treatment. The objective of this knowledge formalisation effort is to create a case-based reasoning application for recommending a treatment process of gold ores. We describe a twofold approach to formalise the necessary knowledge. First, formalising human expert knowledge about gold mining situations enables the retrieval of similar mining contexts and respective process chains, based on prospection data gathered from a potential gold mining site. The second aspect of our approach formalises empirical knowledge on hydrometallurgical treatments. The latter, not described in this paper, will enable us to evaluate and, where needed, redesign the process chain that was recommended by the first aspect of our approach. The main problems with the formalisation of knowledge in the gold ore refinement domain are the divers...

Web 2.0 content, including blogs, forum posts and tweets, is mostly expressed in an unsystematic ... more Web 2.0 content, including blogs, forum posts and tweets, is mostly expressed in an unsystematic manner. Due to this reason, retrieving and reusing this content has become challenging. As a solution, Reichle et al. presented a novel architecture named SEASALT. A main feature of the SEASALT architecture is the use of topic agents implemented as topic specific Case-based reasoning (CBR) systems. Another key component of the SEASALT architecture is the Apprentice Agent which supports a knowledge engineer in the SEASALT Architecture by automatically extracting vocabulary items and taxonomic similarity measures for the CBR-based topic agents from a virtual community of experts, comprising the knowledge input for the SEASALT Architecture. A first implementation of such an apprentice agent was presented by Bach et al. with the Knowledge Extraction workbench (KEWo) which extracted vocabulary items and similarity measures form an online community of travel medicine experts. The work presente...

MedCIRCLE (www.medcircle.info) is a semantic web project to develop and promote technologies able... more MedCIRCLE (www.medcircle.info) is a semantic web project to develop and promote technologies able to guide consumers to trustworthy health information on the Internet and to establish a global web of trust for networked health information. Gateway sites for consumer health information (CisMEF, AQU-MED, Certified Medical Web Site Seal ofMETGES online) will use HIDDEL metadata (Health Information Disclosure, Description and Evaluation Language, expressed in XMI/RDF Syntax) to make their annotation and evaluation data machineprocessable and accessible for software-agents. Other health subject gateways, accreditation, or rating services are invited to join the collaboration by implementing HIDDEL on their gateways. Expressing self-descriptive or third-party evaluations a machine-processableformat allows intelligent agents or client-side software to harvest statements and opinions about the trustworthiness ofother websites and assist users in selecting trustworthy websites. The MedCIRCLE project builds on, expands and continues work on rating health information on the Internet piloted within the MedCERTAIN project. While MedCERTAINprovided the core technologies and software for rating and "trustmarking" health tnformation, MedCIRCLE is built around these technologies and involves a wider medical community to assess health information, demonstrating the power of collaborative and interoperable evaluations on the world-wide-web. Other specific aims include refinement and expansion of HIDDEL, to become a standard vocabulary and interchange format for selfand third-party ratings of health information.

Explanation-aware Computing, 2009

... Semantic Web and Web 2.0. M Greaves, P Mika in Web Semantics Science Services and Agents on t... more ... Semantic Web and Web 2.0. M Greaves, P Mika in Web Semantics Science Services and Agents on the World Wide Web (2008). 2 readers Save reference to library · Related research.Semantic Web or Web 2.0? Socialization of the Semantic Web. ...

... VIII Organization Program Committee Agnar Aamodt, Norwegian University of Science and Technol... more ... VIII Organization Program Committee Agnar Aamodt, Norwegian University of Science and Technology, Norway Varol Akman, Bilkent University, Turkey Elena Andonova, New Bulgarian University, Bulgaria Nicholas Asher, IRIT, France, and University of Texas, USA John ...

Teaching machines to understand human communication is one of the central goals of artificial int... more Teaching machines to understand human communication is one of the central goals of artificial intelligence. Psychological research indicates that human associations are an essential requirement to understand human communication. In this paper the hypothesis is presented that simulating human associations with the help of Linked Data could improve text understanding capabilities of machines. To investigate whether human associations can be simulated with Linked Data, two preliminary problems are identified: (i) A reasonable ground truth for human associations is lacking and (ii) human associations have different strengths while Linked Data treats all triples equally and does not provide edge weights. To overcome these problems, two ideas for web games in accordance with Luis von Ahn's Games with a Purpose are proposed trying to turn the tedious acquisition processes into fun games. The resulting datasets are then to be used for quantitative comparisons of human associations and Linked Data.

Research on explanation in Case-Based Reasoning (CBR) is a topic that gains momentum. In this con... more Research on explanation in Case-Based Reasoning (CBR) is a topic that gains momentum. In this context, fundamental issues on what are and to which end do we use explanations have to be reconsidered. This article presents a prelimenary outline of the combination of two recently proposed classifications of explanations based on the type of the explanation itself and user goals which should be fulfilled.

The information extraction system iDocument interactively extracts information from texts such as... more The information extraction system iDocument interactively extracts information from texts such as instances and relations with respect to existing background knowledge. An extraction process creates weighted hypotheses describing indications of relevant information. During execution, each process step records its output into an instantiated process model. We reused these bits of information for generating conceptual, functional as well as causal explanations. In order to visualise explanations, our component utilises different mechanisms for textual, explorative, and pictorial rendering styles.

... Maguitman (Indiana University, USA) Heiko Maus (DFKI GmbH, Kaiserslautern, Germany) Enrico Ru... more ... Maguitman (Indiana University, USA) Heiko Maus (DFKI GmbH, Kaiserslautern, Germany) Enrico Rukzio (University of Munich, Germany) Thomas Strang (DLR, Germany) Page 9. Table of Contents Using Activity Theory to Model Context Awareness Anders Kofod-Petersen, Jorg ...

The information extraction system iDocument interactively extracts information from text such as ... more The information extraction system iDocument interactively extracts information from text such as instances and relations with respect to existing background knowledge. An extraction process creates weighted recommendations describing indications of relevant information. During execution, each process step records its output into an instantiated process model. We reused these bits of information for generating conceptual, functional as well as causal explanations. The purpose of these explanations is to illustrate the evolution of recommendations for convincing users of their validity. In order to visualise explanations, our component utilises different mechanisms for textual, tabular, and graphical rendering styles.

Lecture Notes in Computer Science, 2005

Having people from two sciences come together appears to be a difficult task, especially when one... more Having people from two sciences come together appears to be a difficult task, especially when one of the sciences has a tradition that can be counted in millennia and where the other one some decades ago simply did not exist. Todays talking about ontologies in informatics (computer science), for instance, can easily be misleading. The term is borrowed from philosophy

KI - Künstliche Intelligenz, 2014

ABSTRACT This paper describes an approach to externalising and formalising expert knowledge invol... more ABSTRACT This paper describes an approach to externalising and formalising expert knowledge involved in the design and evaluation of hydrometallurgical process chains for gold ore treatment. The objective was to create a case-based reasoning application for recommending and validating a treatment process of gold ores. We describe a twofold approach. Formalising human expert knowledge about gold mining situations enables the retrieval of similar mining contexts and respective process chains, based on prospection data gathered from a potential gold mining site. Secondly, empirical knowledge on hydrometallurgical treatments is formalised. This enabled us to evaluate and, where needed, redesign the process chain that was recommended by the first aspect of our approach. The main problems with formalisation of knowledge in the domain of gold ore refinement are the diversity and the amount of parameters used in literature and by experts to describe a mining context. We demonstrate how similarity knowledge was used to formalise literature knowledge. The evaluation of data gathered from experiments with an initial prototype workflow recommender, Auric Adviser, provides promising results.

Proceedings of the 21st international conference companion on World Wide Web - WWW '12 Companion, 2012

In this paper we describe the task of automated mining for solutions to highly specific problems.... more In this paper we describe the task of automated mining for solutions to highly specific problems. We do so under the premise of mapping the split view on context, introduced by Brézillon and Pomerol, onto three different levels of abstraction of a problem domain. This is done to integrate the notion of activity or focus and its influence on the context into the mining for a solution. We assume that a problem's context describes key characteristics to be decisive criteria in the mining process to mine successful solutions for it. We further detail on the process of a chain of sub problems and their foci adding up to a meta problem solution and how this can used to mine for such solutions. Through a guiding example we introduce basic steps of the solution mining process and common aspects we deem interesting to be analysed closer in upcoming research on solution mining. We further examine the possible integration of these newly established outlines for automatic solution mining for highly specific problems into a Seasalt exp , a currently developed architecture for explanation-aware extraction and case-based processing of experiences from Internet communities. We thereby gained first insights in issues occurring while trying to integrate automatic solution mining.

Lecture Notes in Computer Science, 2012

The role of maintenance in the domain of case-based reasoning sys- tems is extremely important. T... more The role of maintenance in the domain of case-based reasoning sys- tems is extremely important. Therefore, methods of maintaining case bases using case properties will be presented. Definitions of the case properties (correctness, consistency, incoherence, minimality, and uniqueness) are given. The use of these properties in five experiments is explained, and the results of these experiments on nine real world

ConTag is an approach to generate semantic tag recommendations for doc- uments based on Semantic ... more ConTag is an approach to generate semantic tag recommendations for doc- uments based on Semantic Web ontologies and Web 2.0 services. We designed and im- plemented a process to normalize documents to RDF format, extract document topics using Web 2.0 services and finally match extracted topics to a Semantic Web ontology. Due to ConTag we are able to show that

This paper describes an approach to externalising and formalising expert knowledge involved in th... more This paper describes an approach to externalising and formalising expert knowledge involved in the design and evaluation of hydrometallurgical process chains for gold ore treatment. The objective of this knowledge formalisation effort is to create a case-based reasoning application for recommending a treatment process of gold ores. We describe a twofold approach to formalise the necessary knowledge. First, formalising human expert knowledge about gold mining situations enables the retrieval of similar mining contexts and respective process chains, based on prospection data gathered from a potential gold mining site. The second aspect of our approach formalises empirical knowledge on hydrometallurgical treatments. The latter, not described in this paper, will enable us to evaluate and, where needed, redesign the process chain that was recommended by the first aspect of our approach. The main problems with the formalisation of knowledge in the gold ore refinement domain are the divers...

Web 2.0 content, including blogs, forum posts and tweets, is mostly expressed in an unsystematic ... more Web 2.0 content, including blogs, forum posts and tweets, is mostly expressed in an unsystematic manner. Due to this reason, retrieving and reusing this content has become challenging. As a solution, Reichle et al. presented a novel architecture named SEASALT. A main feature of the SEASALT architecture is the use of topic agents implemented as topic specific Case-based reasoning (CBR) systems. Another key component of the SEASALT architecture is the Apprentice Agent which supports a knowledge engineer in the SEASALT Architecture by automatically extracting vocabulary items and taxonomic similarity measures for the CBR-based topic agents from a virtual community of experts, comprising the knowledge input for the SEASALT Architecture. A first implementation of such an apprentice agent was presented by Bach et al. with the Knowledge Extraction workbench (KEWo) which extracted vocabulary items and similarity measures form an online community of travel medicine experts. The work presente...