24 Hits in 4.6 sec

Compositional Generalization in Semantic Parsing: Pre-training vs. Specialized Architectures [article]

Daniel Furrer, Marc van Zee, Nathan Scales, Nathanael Schärli
2021 arXiv   pre-print
We investigate state-of-the-art techniques and architectures in order to assess their effectiveness in improving compositional generalization in semantic parsing tasks based on the SCAN and CFQ datasets  ...  generalization on SCAN or in the area of algorithm learning fail to lead to significant improvements.  ...  for being involved in many of the discussions around our progress and providing useful insights.  ... 
arXiv:2007.08970v3 fatcat:g2zntgpearcclmqfjttfvjowke

Towards a service-oriented architecture for a mobile assistive system with real-time environmental sensing

Darpan Triboan, Liming Chen, Feng Chen, Zumin Wang
2016 Tsinghua Science and Technology  
The system provides a base that can be further extended in many areas of AAL systems, including composite AR.  ...  The system architecture brings together the serviceoriented architecture (SOA), semantic web technologies, and other methods to address some of the shortcomings of the preceding system implementations  ...  Acknowledgments The authors gratefully acknowledge the contributions of Simon Forest for the implementation, deployment, and testing of the system.  ... 
doi:10.1109/tst.2016.7787002 fatcat:4yr4u6lqmvgphngmrjtaqkqqgi

Message Passing for Complex Question Answering over Knowledge Graphs

Svitlana Vakulenko, Javier David Fernandez Garcia, Axel Polleres, Maarten de Rijke, Michael Cochez
2019 Proceedings of the 28th ACM International Conference on Information and Knowledge Management - CIKM '19  
Our error analysis reveals correct answers missing from the benchmark dataset and inconsistencies in the DBpedia knowledge graph.  ...  First, we identify entity, relationship, and class names mentioned in a natural language question, and map these to their counterparts in the graph.  ...  (861213), Ahold Delhaize, the Association of Universities in the Netherlands (VSNU), and the Innovation Center for Artificial Intelligence (ICAI).  ... 
doi:10.1145/3357384.3358026 dblp:conf/cikm/VakulenkoGPRC19 fatcat:5geuk55lgvfvjgpo4nutrpsfv4

A semantics-based approach to sensor data segmentation in real-time Activity Recognition

Darpan Triboan, Liming Chen, Feng Chen, Zumin Wang
2019 Future generations computer systems  
One challenge in AR is the segmentation of observed sensor events when interleaved or concurrent activities of daily living (ADLs) are performed.  ...  KD approach is where domain experts in the field of interest conceptualise and intricately describe factual elements of the being into a model that is interlinked, known as the ontological model.  ...  Similarly, work in [26] proposed C-SPARQL, an extension to SPARQL Protocol and RDF Query Language (SPARQL) where individual sensor events in a stream are annotated with a timestamp and continuously queried  ... 
doi:10.1016/j.future.2018.09.055 fatcat:imcpbiowxzfsnffydhwr34kjfu

Entities as Topic Labels: Combining Entity Linking and Labeled LDA to Improve Topic Interpretability and Evaluability

Anne Lauscher, Pablo Ruiz Fabo, Federico Nanni, Simone Paolo Ponzetto
2016 Italian Journal of Computational Linguistics  
We illustrate the potential of the approach by applying it to three datasets, namely the transcription of speeches from the European Parliament fifth mandate, the Enron Corpus and the Hillary Clinton Email  ...  Dataset.  ...  Acknowledgments We want to thank all the people that used the first version of our evaluation platform at the 2016 Digital Humanities Conference in Krakow for providing us an initial gold standard and  ... 
doi:10.4000/ijcol.392 fatcat:5ns4ywz6tbcjhhgviqqapenyee

Knowledge-based Conversational Search [article]

Svitlana Vakulenko
2019 arXiv   pre-print
a more pro-active role in the course of a dialogue interaction.  ...  In the third research chapter, we propose a novel approach for complex question answering from a knowledge graph that surpasses the current state-of-the-art results in terms of both efficacy and efficiency  ...  A core aspect of QAmp is in disentangling reasoning from the question interpretation process.  ... 
arXiv:1912.06859v1 fatcat:rab6kemqujflrobib7lvvy6hue

Bioinformatics Mining and Modeling Methods for the Identification of Disease Mechanisms in Neurodegenerative Disorders

Martin Hofmann-Apitius, Gordon Ball, Stephan Gebel, Shweta Bagewadi, Bernard de Bono, Reinhard Schneider, Matt Page, Alpha Kodamullil, Erfan Younesi, Christian Ebeling, Jesper Tegnér, Luc Canard
2015 International Journal of Molecular Sciences  
Since the decoding of the Human Genome, techniques from bioinformatics, statistics, and machine learning have been instrumental in uncovering patterns in increasing amounts and types of different data  ...  Our review illustrates the challenges entailed in integrating heterogeneous, multiscale and multimodal information in the area of neurology in general and neurodegeneration in particular.  ...  Acknowledgments: The authors would like to thank the entire AETIONOMY consortium for valuable  ... 
doi:10.3390/ijms161226148 pmid:26690135 pmcid:PMC4691095 fatcat:son7r6tkxfgfvfe6apxejr3p24

A Neural-Symbolic Framework for Mental Simulation [article]

Michael Kissner
2020 arXiv   pre-print
From what it learned through observation, the part for intuitive physics infers all the required physical properties of the objects in a scene, enabling predictions.  ...  By means of lifelong meta-learning, the capsule network is expanded and trained continuously, in order to better adapt to its environment with each iteration.  ...  In this chapter we present these concepts and the notation we use. Quotient Spaces To introduce quotient topologies, we need the notion of a topological space.  ... 
arXiv:2008.02356v1 fatcat:ojhlrvykfjd4rmw2uudbroysfa

7.2 Marketplace – Implementation

Matej Ďurčo, Laure Barbot, Klaus Illmayer, Sotiris Karampatakis, Frank Fischer, Yoann Moranville, Joshua Tetteh Ocansey, Stefan Probst, Michał Kozak, Stefan Buddenbohm, Seung-Bin Yim
2021 Zenodo  
release of the application (in December 2021).  ...  Its main purpose is to describe the actual implementation of the SSH Open Marketplace application on the background of the system specification (delivered in 2019 as D7.1 System Specification - SSH Open  ...  Seeing the developments at the EOSC level, where the notion of "resource" is being gradually expanded beyond services to encompass datasets, training materials and other information objects, is gratifying  ... 
doi:10.5281/zenodo.5749464 fatcat:brzjrfngxfdgheu3cc4ftm3ceu

Wikipedia Research and Tools: Review and Comments

Finn Årup Nielsen
2012 Social Science Research Network  
I here give an overview of Wikipedia and wiki research and tools. Well over 1,000 reports have been published in the field and there exist dedicated scientific meetings for Wikipedia research.  ...  It is not possible to give a complete review of all material published. This overview serves to describe some key areas of research. i  ...  corpus. 152 The category network forms another dataset.  ... 
doi:10.2139/ssrn.2129874 fatcat:h4znerp2efhn5j5bdi5rl7addi

Data in Context: How Digital Transformation Can Support Human Reasoning in Cyber-Physical Production Systems

Romy Müller, Franziska Kessler, David W. Humphrey, Julian Rahm
2021 Future Internet  
These technologies enable the modelling of system relations, the integration of data from different sources, and the connection of the present situation with historical data.  ...  The present article presents a selection of the psychological literature in four areas relevant to contextualization: information sampling, information integration, categorization, and causal reasoning  ...  The notion of sampling biases differs from reasoning biases in that it stresses that bias already is present in the information sources.  ... 
doi:10.3390/fi13060156 fatcat:nz42sfagmvannmetb4zibm3fqu

A Framework for Web Science

Tim Berners-Lee, Daniel J. Weitzner, Wendy Hall, Kieron O'Hara, Nigel Shadbolt, James A. Hendler
2006 Foundations and Trends® in Web Science  
This text sets out a series of approaches to the analysis and synthesis of the World Wide Web, and other web-like information structures.  ...  A comprehensive set of research questions is outlined, together with a sub-disciplinary breakdown, emphasising the multi-faceted nature of the Web, and the multi-disciplinary nature of its study and development  ...  helped shape our ideas of what the science of the Web consists in.  ... 
doi:10.1561/1800000001 fatcat:ref26ejozzhsxbaw32xckem2ca

Complex Question Answering over Large-scale Knowledge Bases

challenges existing in previous state-of-the-art question answering systems.  ...  Empirical studies over large-scale CQA datasets not only indicate that our proposed approach is effective as it outperforms state-of-the-art methods significantly and also shed light on the role that specific  ...  It is hard to disentangle the contribution of the two types of knowledge.  ... 
doi:10.26180/15073101.v1 fatcat:dcwnqdqyrzavtb3dyggtgep64i

Data in context: How digital transformation can support human reasoning in cyber-physical production systems [article]

Romy Müller, Franziska Kessler, David W. Humphrey, Julian Rahm
2021 arXiv   pre-print
These technologies enable the modelling of system relations, the integration of data from different sources, and the connection of the present situation with historical data.  ...  We then present a selection of technologies that have the potential to foster contextualization.  ...  Acknowledgments We want to thank Annerose Braune for helpful comments on an earlier version of the manuscript.  ... 
arXiv:2103.17095v1 fatcat:jmdjju4dbbhzrp2zldhzdecyze

Ontology Database: A New Method for Semantic Modeling and an Application to Brainwave Data [chapter]

Paea LePendu, Dejing Dou, Gwen A. Frishkoff, Jiawei Rong
Lecture Notes in Computer Science  
In contrast with existing knowledge-based approaches, we expend additional space in the database to reduce reasoning at query time.  ...  We applied our methodology to the study of brain electroencephalographic (EEG and ERP) data.  ...  Acknowledgements We thank the other members in the NEMO working project group, and in particular Robert Frank, Allen Malony and Don Tucker, for their collaboration on related work.  ... 
doi:10.1007/978-3-540-69497-7_21 fatcat:zgklhqct6jdihojwl5wdxc4bfa
« Previous Showing results 1 — 15 out of 24 results