Filters








4,565 Hits in 13.5 sec

An unsupervised data-driven method to discover equivalent relations in large Linked Datasets

Ziqi Zhang, Anna Lisa Gentile, Eva Blomqvist, Isabelle Augenstein, Fabio Ciravegna, Michelle Cheatham, Isabel F. Cruz, Jérôme Euzenat, Catia Pesquita, Michelle Cheatham, Isabel F. Cruz, Jérôme Euzenat (+1 others)
2016 Semantic Web Journal  
of relations, and an unsupervised clustering process to discover groups of equivalent relations across different schemata.  ...  issue particularly in very large Linked Dataset created automatically from heterogeneous resources, or integrated from multiple datasets.  ...  Acknowledgements Part of this research has been sponsored by the EP-SRC funded project LODIE: Linked Open Data for Information Extraction, EP/J019488/1.  ... 
doi:10.3233/sw-150193 fatcat:odzg7ctdg5avxbjwzsmmyubkai

Special issue on ontology and linked data matching

Michelle Cheatham, Isabel Cruz, Jérôme Euzenat, Catia Pesquita, Michelle Cheatham, Isabel F. Cruz, Jérôme Euzenat, Catia Pesquita
2016 Semantic Web Journal  
The paper "An unsupervised data-driven method to discover equivalent relations in large Linked Datasets" by Zhang, Gentile, Blomqvist, Augenstein, and Ciravegna takes on the problem of finding equivalent  ...  If the datasets to be linked are very large, this creates a bottleneck.  ... 
doi:10.3233/sw-160251 fatcat:pifod66bobbehfqjxiy3civfje

Linked Open Vocabularies (LOV): A gateway to reusable semantic vocabularies on the Web

Pierre-Yves Vandenbussche, Ghislain A. Atemezing, María Poveda-Villalón, Bernard Vatant, Michel Dumontier
2016 Semantic Web Journal  
of relations, and an unsupervised clustering process to discover groups of equivalent relations across different schemata.  ...  issue particularly in very large Linked Dataset created automatically from heterogeneous resources, or integrated from multiple datasets.  ...  Acknowledgements Part of this research has been sponsored by the EP-SRC funded project LODIE: Linked Open Data for Information Extraction, EP/J019488/1.  ... 
doi:10.3233/sw-160213 fatcat:fxa3lqczk5bolnla2oom7fgg3u

A Data-Driven Approach for Semantic Role Labeling from Induced Grammar Structures in Language [article]

Vivek Datla, David Lin, Max Louwerse, Abhinav Vishnu
2016 arXiv   pre-print
In this paper we develop a data-driven approach to identifying semantic roles, the approach is entirely unsupervised up to the point where rules need to be learned to identify the position the semantic  ...  Semantic roles play an important role in extracting knowledge from text. Current unsupervised approaches utilize features from grammar structures, to induce semantic roles.  ...  However, even though these methods do not need a large corpus for role labeling, they do require (large) human annotated data for building the structures (e.g. dependency tree, part-of-speech and constituent  ... 
arXiv:1606.06274v1 fatcat:y4jix5sqbna75ck7d3rbw66azq

Data-driven shape analysis and processing

Kai Xu, Vladimir G. Kim, Qixing Huang, Niloy Mitra, Evangelos Kalogerakis
2016 SIGGRAPH ASIA 2016 Courses on - SA '16  
Data-driven methods serve an increasingly important role in discovering geometric, structural, and semantic relationships between shapes.  ...  In contrast to knowledge driven methods, data-driven techniques learn representations and parameters from data.  ...  each shape in a large dataset.  ... 
doi:10.1145/2988458.2988473 dblp:conf/siggraph/0004KHMK16 fatcat:tefja76ijnclzmpux2iaj45zgu

Link Prediction in Heterogeneous Collaboration Networks [chapter]

Xi Wang, Gita Sukthankar
2014 Lecture Notes in Social Networks  
In this article, we study both supervised and unsupervised link prediction in networks where instances can simultaneously belong to multiple communities, engendering different types of collaborations.  ...  We also compare the unsupervised performance of the individual features used within LPSF with two new diffusion-based methods: LPDP (Link Prediction using Diffusion Process) and LPDM (Link Prediction using  ...  proposed an unsupervised extension of the common Adamic/Adar method to predict heterogeneous relationships in multi-relational networks [20] .  ... 
doi:10.1007/978-3-319-12188-8_8 dblp:series/lnsn/WangS14 fatcat:sojaw6bghbhi3dudptvylbskdy

On the discovery of social roles in large scale social systems

Derek Doran
2015 Social Network Analysis and Mining  
This article presents a data-driven approach for the discovery of social roles in large scale social systems.  ...  Motivated by an analysis of the present art, the method discovers roles by the conditional triad censuses of user ego-networks, which is a promising tool because they capture the degree to which basic  ...  Linking representation with social theory As discussed in Section 2.4, many data-driven analyses select a large collection of structural, user, and relationship attributes, and use them all to discover  ... 
doi:10.1007/s13278-015-0290-0 fatcat:vhopvrh6l5cgre7xkqxpr6xl4i

Discovering Missing Semantic Relations between Entities in Wikipedia [chapter]

Mengling Xu, Zhichun Wang, Rongfang Bie, Juanzi Li, Chen Zheng, Wantian Ke, Mingquan Zhou
2013 Lecture Notes in Computer Science  
In this paper, we propose an approach for automatically discovering the missing entity links in Wikipedia's infoboxes, so that the missing semantic relations between entities can be established.  ...  Wikipedia's infoboxes contain rich structured information of various entities, which have been explored by the DBpedia project to generate large scale Linked Data sets.  ...  first uses a unsupervised extraction algorithm to identify and rank mentions, and then combines both knowledge-based approach and data-driven method to discover new entity links. -M&W.  ... 
doi:10.1007/978-3-642-41335-3_42 fatcat:gdcjpxlb2vbatds5gspctccfc4

Openaire2020 D10.2 - Clustering Algorithms

Omiros Metaxas, Theodoros Giannakopoulos
2016 Zenodo  
datasets discovering mine discovered itemset D10.2 Clustering algorithms Below we present some related statistics and outcomes related to funded research analysis based on OpenAIRE information  ...  Probabilistic latent semantic indexing Latent Dirichlet allocation Indexing by latent semantic analysis On an equivalence between PLSI and LDA Fast Algorithms for Mining Association Rules in Large  ...  FIGURE 12: EXAMPLE OF PRE-CLASSIFICATION AND CLASSIFICATION APPLIED ON AN UNKNOWN DOCUMENT  ... 
doi:10.5281/zenodo.1257349 fatcat:urryukf52barnfmymb6noquzq4

Enhancing White-Box Machine Learning Processes by Incorporating Semantic Background Knowledge [chapter]

Gilles Vandewiele
2017 Lecture Notes in Computer Science  
Currently, most of white-box machine learning techniques are purely data-driven and ignore prior background and expert knowledge.  ...  The goal of this research proposal is to enhance the predictive performance and required training time of white-box models by incorporating the vast amount of available knowledge in the pre-processing,  ...  Acknowledgements I would like to thank my promoters prof. Filip De Turck and dr. Femke Ongenae from Ghent University for their support and valuable input in the realization of this work.  ... 
doi:10.1007/978-3-319-58451-5_21 fatcat:rhktabo57bdz5jibfpq7bgsovu

Unsupervised Representation Learning by Discovering Reliable Image Relations [article]

Timo Milbich, Omair Ghori, Ferran Diego, Björn Ommer
2019 arXiv   pre-print
Annotating the quadratic number of pairwise relations between training images is simply not feasible, while unsupervised inference is prone to noise, thus leaving the vast majority of these relations to  ...  In experiments, our approach shows state-of-the-art performance on unsupervised classification on ImageNet with 46.0% and competes favorably on different transfer learning tasks on PASCAL VOC.  ...  He is currently a senior data scientist at AGT International and is also pursuing his PhD at the Heidelberg Collaboratory for Image Processing at Heidelberg University.  ... 
arXiv:1911.07808v1 fatcat:syomuszwfjaflauzylsfebc3ia

Knowledge management technologies and applications: A literature review

Xiaomi An, Wang Wang
2010 2010 IEEE International Conference on Advanced Management Science(ICAMS 2010)  
Data mining is an area of research and study within a computer science discipline involving to make out the meaning and interpret the information or data, something that repeats in a predictable way which  ...  technology with a plan or intention or an idea or invention to help sell or publicize a commodity in view of such as AI, database systems, ML and statistics.  ...  DOMAIN-DRIVEN DATA MINING REQUIREMENTS By considering this new approach in finding data pattern, a solution towards fulfilling domain-driven data mining requirements can be made by  Finding the frequent  ... 
doi:10.1109/icams.2010.5553046 fatcat:ips3f4muafdkdcbxj5r7l4uraq

Data-Driven Shape Analysis and Processing [article]

Kai Xu, Vladimir G. Kim, Qixing Huang, Evangelos Kalogerakis
2015 arXiv   pre-print
Data-driven methods play an increasingly important role in discovering geometric, structural, and semantic relationships between 3D shapes in collections, and applying this analysis to support intelligent  ...  In contrast to traditional approaches, a key feature of data-driven approaches is that they aggregate information from a collection of shapes to improve the analysis and processing of individual shapes  ...  In unsupervised mode, the corresponding labeling accuracy is 89.9% in the COSEG dataset on average. of data-driven methods for segmentation in the Princeton Segmentation Benchmark (PSB) and COSEG datasets  ... 
arXiv:1502.06686v1 fatcat:upajios4y5a6dgf2zw7faqai4a

Machine Learning Algorithms for Smart Data Analysis in Internet of Things Environment: Taxonomies and Research Trends

Alsharif, Kelechi, Yahya, Chaudhry
2020 Symmetry  
This study is limited to supervised and unsupervised machine learning (ML) techniques, regarded as the bedrock of the IoT smart data analysis.  ...  This study includes reviews and discussions of substantial issues related to supervised and unsupervised machine learning techniques, highlighting the advantages and limitations of each algorithm, and  ...  The input experimental data x represents an n dimensional, while individual dimension links to an explicit feature or a specific variable.  ... 
doi:10.3390/sym12010088 fatcat:darnmyhy2jbinlxy7aj5vlc57i

PathCORE-T: identifying and visualizing globally co-occurring pathways in large transcriptomic compendia

Kathleen M. Chen, Jie Tan, Gregory P. Way, Georgia Doing, Deborah A. Hogan, Casey S. Greene
2018 BioData Mining  
Results: We developed PathCORE-T framework by implementing existing methods to identify pathway-pathway transcriptional relationships evident across a broad data compendium.  ...  We demonstrate PathCORE-T by analyzing an existing eADAGE model of a microbial compendium and building and analyzing NMF features from the TCGA dataset of 33 cancer types.  ...  Acknowledgements The authors would also like to thank Daniel Himmelstein, Dongbo Hu, Kurt Wheeler, and René Zelaya for helping to review the source code.  ... 
doi:10.1186/s13040-018-0175-7 pmid:29988723 pmcid:PMC6029133 fatcat:a3iahaosbvbfzb674ayexrahzm
« Previous Showing results 1 — 15 out of 4,565 results