20,584 Hits in 5.2 sec

Enriching Artificial Intelligence Explanations with Knowledge Fragments

Jože Rožanec, Elena Trajkova, Inna Novalija, Patrik Zajec, Klemen Kenda, Blaž Fortuna, Dunja Mladenić
2022 Future Internet  
Furthermore, the insights into the models' rationale can be enriched with domain knowledge.  ...  This research builds explanations considering feature rankings for a particular forecast, enriching them with media news entries, datasets' metadata, and entries from the Google knowledge graph.  ...  Media events, Media events' keywords, external datasets and Google KG correspond to contextual information displayed for each forecast explanation.  ... 
doi:10.3390/fi14050134 fatcat:ssxjtfubyfeaxegwen37duxktm

Enriching Artificial Intelligence Explanations with Knowledge Fragments [article]

Jože M. Rožanec, Elena Trajkova, Inna Novalija, Patrik Zajec, Klemen Kenda, Blaž Fortuna, Dunja Mladenić
2022 arXiv   pre-print
Furthermore, the insights into models' rationale can be enriched with domain knowledge.  ...  Artificial Intelligence models are increasingly used in manufacturing to inform decision-making. Responsible decision-making requires accurate forecasts and an understanding of the models' behavior.  ...  Media Events, Media Events' Keywords, External Datasets and Google KG correspond to contextual information displayed for each forecast explanation.  ... 
arXiv:2204.05579v1 fatcat:ylddqslbkjgfzg36cyvhyva23a

Semantically Enhancing Multimedia Lifelog Events [chapter]

Peng Wang, Alan Smeaton, Alessandra Mileo
2014 Lecture Notes in Computer Science  
In this paper we demonstrate the potential of semantic web technologies for analysing lifelogs by automatically augmenting descriptions of lifelog events.  ...  Analysing lifelogs with a view to supporting contentbased access, presents many challenges.  ...  Conclusion and Future Work This paper introduced a method for semantic enhancement of multimedia lifelog events to improve their interpretation by leveraging external knowledge.  ... 
doi:10.1007/978-3-319-13168-9_17 fatcat:pxmtravzvjd43d2vxmxma6guna

A Query Expansion Approach Using Entity Distribution Based on Markov Random Fields [chapter]

Rui Li, Linxue Hao, Xiaozhao Zhao, Peng Zhang, Dawei Song, Yuexian Hou
2015 Lecture Notes in Computer Science  
In this paper, we propose a novel query expansion technique with knowledge graph (KG) based on the Markov random fields (MRF) model to enhance retrieval performance.  ...  Knowledge graph is often used for knowledge inference and entity search, however, the potential ability of its entities and properties for better improving search performance in query expansion remains  ...  In summary, the MRF-KG model is more efficient than MRF and LCE with leveraging external knowledge graph, making it richer and more accurate for entity analysis in queries.  ... 
doi:10.1007/978-3-319-28940-3_31 fatcat:na3f24ipojh2nkuboqh4iimj3i

Leveraging Graph Analytics for Energy Efficiency Certificates

Panagiotis Kapsalis, Giorgos Kormpakis, Konstantinos Alexakis, Dimitrios Askounis
2022 Energies  
In this paper, we propose an architecture for a Reasoning Engine, a mechanism that provides intelligent querying, insights and search capabilities, by leveraging technologies that will be described below  ...  Subsequently, several use cases, where related technologies were used to address real-world challenges, are presented.  ...  To be more specific, the Reasoning Engine is a mechanism that provides intelligent querying, insights, and search capabilities by leveraging the available knowledge for the digital twin and analytics services  ... 
doi:10.3390/en15041500 fatcat:uee2dsxhzrestjuv2tbro4wvqy

Adaptive Knowledge-Enhanced Bayesian Meta-Learning for Few-shot Event Detection [article]

Shirong Shen and Tongtong Wu and Guilin Qi and Yuan-Fang Li and Gholamreza Haffari and Sheng Bi
2021 arXiv   pre-print
Furthermore, as external knowledge typically provides limited and imperfect coverage of event types, we introduce an adaptive knowledge-enhanced Bayesian meta-learning method to dynamically adjust the  ...  To tackle the issue of low sample diversity in few-shot ED, we propose a novel knowledge-based few-shot event detection method which uses a definition-based encoder to introduce external event knowledge  ...  Acknowledgement Research in this paper was partially supported by the Fundamental Research Funds for the Central Universities (2242021k10011).  ... 
arXiv:2105.09509v2 fatcat:n6hraqvhi5bgjj6jovcwhsvaue

Incorporating Semantic Knowledge into Dynamic Data Processing for Smart Power Grids [chapter]

Qunzhi Zhou, Yogesh Simmhan, Viktor Prasanna
2012 Lecture Notes in Computer Science  
Semantic Web is promising to model diverse Smart Grid domain knowledge for enhanced situation awareness and response by multi-disciplinary participants.  ...  Semantic Web allows us to model and query time-invariant or slowly evolving knowledge using ontologies.  ...  Further, external models (such as Weather) can be easily integrated. Semantic model based asset management hence ensures rapid and extensible knowledge transference and integration.  ... 
doi:10.1007/978-3-642-35173-0_17 fatcat:wfcsba2p7rcdrpv4cywtzvhrym

Semantic XAI for contextualized demand forecasting explanations [article]

Jože M. Rožanec, Dunja Mladenić
2021 arXiv   pre-print
The provided explanations combine concepts describing features relevant to a particular forecast, related media events, and metadata regarding external datasets of interest.  ...  We link domain knowledge, forecasted values, and forecast explanations in a Knowledge Graph. The ontology and dataset we developed for this use case are publicly available for further research.  ...  Those new keywords are used to query for external datasets that could enrich the existing demand forecasting model.  ... 
arXiv:2104.00452v1 fatcat:4smbknh6b5dpdchq2azcjybeee

Flexible Interactive Retrieval SysTem 3.0 for Visual Lifelog Exploration at LSC 2022

Nhat Hoang-Xuan, Hoang-Phuc Trang-Trung, E-Ro Nguyen, Thanh-Cong Le, Mai-Khiem Tran, Tu-Khiem Le, Van-Tu Ninh, Cathal Gurrin, Minh-Triet Tran
2022 Proceedings of the 5th Annual on Lifelog Search Challenge  
For LSC'22, we develop FIRST 3.0, a novel and flexible system that leverages expressive cross-domain embeddings to enhance the searching process.  ...  We also propose to augment our system with an external search engine to help our system with initial visual examples for unfamiliar concepts.  ...  However, by allowing the retrieval process to be guided by external knowledge, we can have an effectively unlimited pool of understood concepts, while leveraging the effectiveness of our searching tool  ... 
doi:10.1145/3512729.3533013 fatcat:coaiyhbhlbh6hgzdpxf7eqsjo4

LifeSeeker 4.0: An Interactive Lifelog Search Engine for LSC'22

Thao-Nhu Nguyen, Tu-Khiem Le, Van-Tu Ninh, Minh-Triet Tran, Thanh Binh Nguyen, Graham Healy, Sinéad Smyth, Annalina Caputo, Cathal Gurrin
2022 Proceedings of the 5th Annual on Lifelog Search Challenge  
In LifeSeeker 4.0, we focus on enhancing our previous system to allow users who have little to no knowledge of underlying system functioning and lifelog data to use it with ease by not only enhancing the  ...  Event clustering is also improved in this version to increase user experience by reducing the occurrence of repeated images, and hence decreasing the search time.  ...  the CLIP model to the searching mechanism, and event clustering.  ... 
doi:10.1145/3512729.3533014 fatcat:omyjkjszdzdhtkwzmdnhdowdgi

The use of topic evolution to help users browse and find answers in news video corpus

Shi-Yong Neo, Yuanyuan Ran, Hai-Kiat Goh, Yantao Zheng, Tat-Seng Chua, Jintao Li
2007 Proceedings of the 15th international conference on Multimedia - MULTIMEDIA '07  
In this paper, we propose an enhancement to news video searching by leveraging extractable video semantics coupled with relevant external information resources to support event-based analysis; leading  ...  For QA, we employ extensive query analysis to obtain various query features in addition to the topic hierarchical structures to answer both context-oriented and visual-oriented questions.  ...  With this hindsight, [30] extended the techniques from text processing to video QA by modeling the Web and linguistic knowledge for effective QA.  ... 
doi:10.1145/1291233.1291278 dblp:conf/mm/NeoRGZCL07 fatcat:4eacbql6yve5levi6sdspefvza

Integrating Unstructured and Structured Knowledge with the KnowledgeStore [chapter]

Marco Rospocher, Francesco Corcoglioniti, Roldano Cattoni, Bernardo Magnini, Luciano Serafini
2015 Lecture Notes in Computer Science  
The KS contributes to bridge the unstructured (e.g., textual document, web pages) and structured (e.g., RDF, LOD) worlds, enabling to jointly store, manage, retrieve, and query, both typologies of contents  ...  We showcase the KnowledgeStore (KS), a scalable, fault-tolerant, and Semantic Web grounded storage system for interlinking unstructured and structured contents.  ...  Acknowledgements The research leading to this paper was supported by the European Union's 7th Framework Programme via the NewsReader Project (ICT-316404).  ... 
doi:10.1007/978-3-319-17966-7_26 fatcat:bsz52uxy7fdm5kijeruusrwbxa

An Ontology for Historical Research Documents [chapter]

Giovanni Adorni, Marco Maratea, Laura Pandolfo, Luca Pulina
2015 Lecture Notes in Computer Science  
In stole we leverage ontologies for describing domain knowledge and providing semantic information integration among data in order to support historians' research.  ...  to find out some unexplored but useful aspects about a particular event or person.  ...  In stole we leverage ontologies for describing domain knowledge and providing semantic information integration among data in order to support historians' research.  ... 
doi:10.1007/978-3-319-22002-4_2 fatcat:2jqma7wphfd2xek4gkruk7eyma

An ontology-based framework for automated code generation of Web AR applications

Lazar Đorđević, Nenad Petrović, Milorad Tošić
2020 Telfor Journal  
In this paper, we propose an ontology-based framework for automated Web AR application code generation leveraging semantic descriptions of application structure and behavior in synergy with domain knowledge  ...  and annotations of building information model (BIM).  ...  If(o instance of 3D model and o instance of Rotates) 19. Generate code for loading and rotating 3D model; 20. End if 21. End for each 22. End for each 23. Append event handler template to output; 24.  ... 
doi:10.5937/telfor2001067q fatcat:rmegzzukbbh7dpt2x453mr5j7q

Managing Semantic Big Data for Intelligence

Anne-Claire Boury-Brisset
2013 Semantic Technologies for Intelligence, Defense, and Security  
The development of this scalable data integration platform rests on the layered dataspace approach, makes use of recent Big Data technologies and leverages ontological models, and semantic-based analysis  ...  Leveraging recent advances in data integration, Semantic Web and Big Data technologies, we are adapting key concepts of unified dataspaces and semantic enrichment for the design and implementation of a  ...  based on the use of ontologies to integrate and semantically enhance data models.  ... 
dblp:conf/stids/Boury-Brisset13 fatcat:j3f4ajty4bbfzozmuvphgwdiia
« Previous Showing results 1 — 15 out of 20,584 results