Enabling experts to build knowledge bases from science textbooks

Chaudhri, Vinay K.; John, Bonnie E.; Mishra, Sunil Kumar; Pacheco, John; Porter, Bruce; Spaulding, Aaron

doi:10.1145/1298406.1298435

Cited by 17 publications

(12 citation statements)

References 10 publications

(10 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…10 A total of six knowledge formulation (KF) SMEs participated, who formulated knowledge on the selected evaluation syllabi in the scientific domains of Chemistry and Biology and tested reasoning with it. These knowledge bases were later used by five Question Formulation (QF) SMEs, with the supportof QF KEs, who formulated selected AP-level questions that were intended to be answered by the system.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

A Formalism and Method for Representing and Reasoning with Process Models Authored by Subject Matter Experts

Gómez-Pérez¹,

Erdmann²,

Greaves

et al. 2013

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

Abstract-Enabling Subject Matter Experts (SMEs) to formulate knowledge without the intervention of Knowledge Engineers (KEs) requires providing SMEs with methods and tools that abstract the underlying knowledge representation and allow them to focus on modeling activities. Bridging the gap between SME-authored models and their representation is challenging, especially in the case of complex knowledge types like processes, where aspects like frame management, data, and control flow need to be addressed. In this paper, we describe how SME-authored process models can be provided with an operational semantics and grounded in a knowledge representation language like F-logic to support process-related reasoning. The main results of this work include a formalism for process representation and a mechanism for automatically translating process diagrams into executable code following such formalism. From all the process models authored by SMEs during evaluation 82 percent were well formed, all of which executed correctly. Additionally, the two optimizations applied to the code generation mechanism produced a performance improvement at reasoning time of 25 and 30 percent with respect to the base case, respectively. 1INTRODUCTIONB UILDING knowledge-based systems is an activity that has been traditionally carried out by a combination of software and knowledge engineers (KEs) and of subject matter experts (SMEs), also known as domain experts. Software engineers (SEs) are focused on architectural and user interface issues related to the development of software. KEs are focused on knowledge acquisition and representation tasks, with the aim of building the required knowledge bases. For these tasks, KEs usually work in collaboration with SMEs, who normally act as repositories of domain knowledge. The combination of KEs and SMEs, although feasible, has two main drawbacks, first characterized as the knowledge acquisition bottleneck [13]: 1) it is costly and 2) it can be error prone, especially in complex domains.A large amount of work in knowledge-based systems in the past three decades, like [11] Among the different types of knowledge that can be used in knowledge-based systems, e.g., factual, rule or causal knowledge, we focus on process knowledge, which is widely used across domains while posing important challenges for knowledge acquisition. A process can be defined as a naturally occurring or designed sequence of changes of properties of a system or object. Examples of processes include the replication of DNA, the mitosis of the cell or a combustion reaction. Processes encapsulate such things as preconditions and postconditions, results, contents, actors or causes and relate to the sequence of operations and involved events taking up time, space, expertise or other resources, which lead to the production of an outcome. For example, consider the case of a complex chemical reaction comprising several steps, with different inputs and outputs, where it is necessary to reason about what would happen at a certain stage if a previou...

show abstract

Section: Discussionmentioning

confidence: 99%

“…However, despite progress shown by existing knowledge acquisition tools like KRAKEN [25], SHAKEN [3] and, more recently, AURA [10] and the Halo extension of the Semantic MediaWiki [18], it is still a complex problem to enable SMEs to capture the knowledge from a domain by themselves, especially for some knowledge types.…”

Section: Introductionmentioning

confidence: 99%

A Formalism and Method for Representing and Reasoning with Process Models Authored by Subject Matter Experts

Gómez-Pérez¹,

Erdmann²,

Greaves

et al. 2013

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

show abstract

“…The question-answering system, along with a separate knowledge acquisition system used to build KBs (not described here, see [14]), was extensively evaluated during May and June 2006. Experts first built KBs about physics, chemistry, and biology (outside the scope of this paper).…”

Section: Evaluation Methodologymentioning

confidence: 99%

Capturing and answering questions posed to a knowledge-based system

Clark

Chaw

Barker

et al. 2007

Proceedings of the 4th International Conference on Knowledge Capture

Self Cite

View full text Add to dashboard Cite

As part of the ongoing project, Project Halo, our goal is to build a system capable of answering questions posed by novice users to a formal knowledge base. In our current context, the knowledge base covers selected topics in physics, chemistry, and biology, and our question set consists of AP (advanced high-school) level examination questions. The task is challenging because the questions are linguistically complex and are often incomplete (assume unstated knowledge), and because the users do not have prior knowledge of the system's contents. Our solution involves two parts: a controlled language interface, in which users reformulate the original natural language questions in a simplified version of English, and a novel problem solver that can elaborate initially inadequate logical interpretations of a question by selecting relevant pieces of knowledge in the knowledge base. An evaluation of the work in 2006 showed that this approach is feasible and that complex, multisentence questions can be posed and answered, thus illustrating novel ways of dealing with the knowledge capture impedance between users and a formal knowledge base, while also revealing challenges that still remain.

show abstract

“…The conducted information security knowledge mappings aimed at incorporating explicit knowledge, which could be easily formalized. Further research efforts, based on existing approaches such as [12], will also concentrate on incorporating tacit knowledge, which is much more difficult to articulate and to formalize than explicit knowledge [27].…”

Section: Knowledge Basementioning

confidence: 99%

Formalizing information security knowledge

Fenz

Ekelhart

2009

Proceedings of the 4th International Symposium on Information, Computer, and Communications Security

168

126

View full text Add to dashboard Cite

Unified and formal knowledge models of the information security domain are fundamental requirements for supporting and enhancing existing risk management approaches. This paper describes a security ontology which provides an ontological structure for information security domain knowledge. Besides existing best-practice guidelines such as the German IT Grundschutz Manual also concrete knowledge of the considered organization is incorporated. An evaluation conducted by an information security expert team has shown that this knowledge model can be used to support a broad range of information security risk management approaches.

show abstract

Enabling experts to build knowledge bases from science textbooks

Cited by 17 publications

References 10 publications

A Formalism and Method for Representing and Reasoning with Process Models Authored by Subject Matter Experts

A Formalism and Method for Representing and Reasoning with Process Models Authored by Subject Matter Experts

Capturing and answering questions posed to a knowledge-based system

Formalizing information security knowledge

Contact Info

Product

Resources

About