An official website of the United States government
Using ontology embeddings with deep learning architectures to improve prediction of ontology concepts from literature
- Award ID(s):
- 1942727
- PAR ID:
- 10539652
- Publisher / Repository:
- CEUR-WS
- Date Published:
- Journal Name:
- CEUR workshop proceedings
- ISSN:
- 1613-0073
- Format(s):
- Medium: X
- Location:
- Brazil
- Sponsoring Org:
- National Science Foundation
More Like this
-
Kirrane, Sabrina; Ngonga Ngomo, Axel-Cyrille; Kirrane, Sabrina; Ngonga Ngomo, Axel-Cyrille (Ed.)Reusing ontologies for new purposes, or adapting them to new use-cases, is frequently difficult. In our experiences, we have found this to be the case for several reasons: (i) differing representational granularity in ontologies and in use-cases, (ii) lacking conceptual clarity in potentially reusable ontologies, (iii) lack and difficulty of adherence to good modeling principles, and (iv) a lack of reuse emphasis and process support available in ontology engineering tooling. In order to address these concerns, we have developed the Modular Ontology Modeling (MOMo) methodology, and its supporting tooling infrastructure, CoModIDE (the Comprehensive Modular Ontology IDE – “commodity”). MOMo builds on the established eXtreme Design methodology, and like it emphasizes modular development and design pattern reuse; but crucially adds the extensive use of graphical schema diagrams, and tooling that support them, as vehicles for knowledge elicitation from experts. In this paper, we present the MOMo workflow in detail, and describe several useful resources for executing it. In particular, we provide a thorough and rigorous evaluation of CoModIDE in its role of supporting the MOMo methodology’s graphical modeling paradigm. We find that CoModIDE significantly improves approachability of such a paradigm, and that it displays a high usability.more » « less
-
Cities are actively creating open data portals to enable predictive analytics of urban data. However, the large number of observable patterns that can be extracted by techniques such as Association Rule Mining (ARM) makes the task of sifting through patterns a tedious and time-consuming task. In this paper, we explore the use of domain ontologies to: (i) filter and prune rules that are specific variations of a more general concept in the ontology, and (ii) replace specific rules by a single "general" rule, with the intent to downsize the number of general rules while keeping the semantics of the larger generated set. We show how the combination of several methods reduces significantly the number of rules thus effectively allowing city administrators to use open data to understand patterns, use patterns for decision-making, and better direct limited government resources.more » « less
-
Abstract The development of semi-automated and automated ontology alignment techniques is an important part of realizing the potential of the Semantic Web. Until very recently, most existing work in this area was focused on finding simple (1:1) equivalence correspondences between two ontologies. However, many real-world ontology pairs involve correspondences that contain multiple entities from each ontology. These ‘complex’ alignments pose a challenge for existing evaluation approaches, which hinders the development of new systems capable of finding such correspondences. This position paper surveys and analyzes the requirements for effective evaluation of complex ontology alignments and assesses the degree to which these requirements are met by existing approaches. It also provides a roadmap for future work on this topic taking into consideration emerging community initiatives and major challenges that need to be addressed.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
