Filters








3,392 Hits in 5.4 sec

Towards End-to-End Transformation of Arbitrary Tables from Untagged Portable Documents (PDF) to Linked Data

Alexey O. Shigarov, Igor Cherepanov, Evgeniy A. Cherkashin, Nikita O. Dorodnykh, Vasiliy V. Khristyuk, Andrey A. Mikhailov, Viacheslav Paramonov, Egor Rozhkow, Alexandr Yu. Yurin
2019 Scientific-practical Workshop Information Technologies: Algorithms, Models, Systems  
We consider some perspective approaches for the deeplearning-based table detection, heuristic-based table structure recognition, rule-based table analysis, and knowledge-based table interpretation.  ...  Our application experience confirms that such solutions are demanded for populating databases and generating ontologies with tabular data being extracted from weakly and semi-structured documents.  ...  Additionally, ad-hoc heuristics can be handcrafted and tuned for various domain-specific PDF documents.  ... 
dblp:conf/itams/ShigarovCCDKMPR19 fatcat:a3pyywle2bbgrms5bgnxvkrway

Towards Aligning Multi-concern Models via NLP

Fatma Basak Aydemir, Fabiano Dalpiaz
2017 2017 IEEE 25th International Requirements Engineering Conference Workshops (REW)  
The design of large-scale complex systems requires their analysis from multiple perspectives, often through the use of requirements models.  ...  Many querying methods exist: Exact match: The ontology contains an entry that is an exact match of the noun. Contains: There is an entry in the ontology that contains the noun, e.g.  ...  This paper paves the way for future work. The focus group confirmed the need for different heuristics based on the individual preferences of the modelers.  ... 
doi:10.1109/rew.2017.82 dblp:conf/re/AydemirD17 fatcat:7nqzk7ykgjhh7jsexwvzulhmxq

Ontology learning for the Semantic Web

A. Maedche, S. Staab
2001 IEEE Intelligent Systems  
We also refer to other techniques for future implementation, such as reverse engineering of ontologies from database schemata or learning from XML documents.  ...  The authors present an ontology-learning framework that extends typical ontology engineering environments by using semiautomatic ontology-construction tools.  ...  Acknowledgments We thank our students, Dirk Wenke, and Raphael Volz for work on OntoEdit and Text-To-Onto.  ... 
doi:10.1109/5254.920602 fatcat:iwtrhonygfeobb3kwkh5n4guwi

Breathing ontological knowledge into feature model synthesis: an empirical study

Guillaume Bécan, Mathieu Acher, Benoit Baudry, Sana Ben Nasr
2015 Empirical Software Engineering  
We develop six heuristics for clustering and weighting the logical, syntactical and semantical relationships between feature names.  ...  Numerous synthesis techniques and tools have been proposed, but only a few consider both configuration and ontological semantics of an FM.  ...  Key findings for RQ2. -The experiment demonstrates that an approach based on ontological heuristics provides the best support for producing ranking lists.  ... 
doi:10.1007/s10664-014-9357-1 fatcat:zyu3s5oyinb65ff3ryhi6jxh34

A Multi-agent Architecture for Labeling Data and Generating Prediction Models in the Field of Social Services [chapter]

Emilio Serrano, Pedro del Pozo-Jiménez, Mari Carmen Suárez-Figueroa, Jacinto González-Pachón, Javier Bajo, Asunción Gómez-Pérez
2017 Communications in Computer and Information Science  
The architecture offers a holistic view of the main challenges involved in labeling data and generating prediction models for social services.  ...  A fundamental reason for this gap is the difficulty in labeling and annotating social services data. Conditions such as social exclusion require a case-by-case debate.  ...  is supported by the "Junta de Castilla y León" under the public contract: "Servicios de elaboración de modelos matemáticos para realizar segmentación poblacional" (A2016/000271); by the EU Programme for  ... 
doi:10.1007/978-3-319-60285-1_15 fatcat:ohqm4j5byvaoveep5vvfwn46tq

Ordering Heuristics for Description Logic Reasoning

Dmitry Tsarkov, Ian Horrocks
2005 International Joint Conference on Artificial Intelligence  
We present a new architecture for Description Logic implementations, a range of new optimisation techniques and an empirical analysis of their effectiveness.  ...  ., configuration [McGuinness & Wright, 1998 ], and reasoning with database schemas and queries [Calvanese et al., 1998b; 1998a] ), they are perhaps best known as the basis for widely used ontology languages  ...  The idea is to make an initial guess based on an analysis of the syntactic structure of the ontology (it should be quite easy to distinguish GALEN-like ontologies from DOLCE and WineFood-like ontologies  ... 
dblp:conf/ijcai/TsarkovH05 fatcat:lmwjh3gfmnau7iegh3cson3p4a

Toward MUI: Ontology assisted global identification of Audio Resources

Giovanni Tummarello, Christian Morbidoni, Dimitrios Kourtesis, Francesco Piazza, Paolo Puliti
2005 Semantic Web Applications and Perspectives  
For machine and individuals to successfully exchange annotations about audio resources, a technique is needed to provide these with stable identifiers.  ...  In this paper we propose ontological definitions of some identification problems and discuss the preliminary conceptual structure of the Music URI Infrastructure (MUI) project.  ...  completely uncorrelated tune.  ... 
dblp:conf/swap/TummarelloMKPP05 fatcat:254gnvvb4zfpbinmowwjnjzxgy

Fast and simple semantic class assignment for biomedical text

K. Bretonnel Cohen, Tom Christiansen, William A. Baumgartner Jr., Karin Verspoor, Lawrence Hunter
2011 Workshop on Biomedical Natural Language Processing  
A simple and accurate method for assigning broad semantic classes to text strings is presented.  ...  The method is to map text strings to terms in ontologies based on a pipeline of exact matches, normalized strings, headword matching, and stemming headwords.  ...  Future work The heuristics that we implemented for extracting headwords from OBO terms were very simple, in keeping with our initial goal of developing an easy, fast method for semantic class assignment  ... 
dblp:conf/bionlp/CohenCBVH11 fatcat:v5ykyxnko5h5zhfb7bojw3cw5y

Entity Identification on the Semantic Web

Alexis Morris, Yannis Velegrakis, Paolo Bouquet
2008 Semantic Web Applications and Perspectives  
In this work we survey a number of entity disambiguation and identification techniques and tools that can be used in semantic web applications and more specifically, into an entity management system for  ...  This ability is of paramount importance for all those applications and systems currently operating in the highly heterogeneous web environment.  ...  It is designed similarly to the Page-Rank algorithm, but uses a news metadata ontology and a natural language processing engine, along with a heuristic/deductive database techniques.  ... 
dblp:conf/swap/MorrisVB08 fatcat:na3x4ec2qrd2lj6s5amjszaznq

Cornetto: A Combinatorial Lexical Semantic Database for Dutch [chapter]

Piek Vossen, Isa Maks, Roxane Segers, Hennie van der Vliet, Marie-Francine Moens, Katja Hofmann, Erik Tjong Kim Sang, Maarten de Rijke
2012 Essential Speech and Language Technology for Dutch  
In addition to the database, there is a toolkit for the acquisition of new concepts and relations, and the tuning and extraction of a domain specific sub-lexicon from a compiled corpus.  ...  Database for Dutch Cornetto: A Combinatorial Lexical Semantic Database for Dutch Cornetto: A Combinatorial Lexical Semantic Database for Dutch For an overview of all semantic relations used  ... 
doi:10.1007/978-3-642-30910-6_10 dblp:series/tanlp/VossenMSVMHSR13 fatcat:zu5fmn2jdresxpz7cts2kforra

Meta-Learning Architectures: Collecting, Organizing and Exploiting Meta-Knowledge [chapter]

Joaquin Vanschoren
2011 Studies in Computational Intelligence  
Planning All possible actions in a KD workflow are described as operations with preconditions and effects, and an AI planner is used to find the most interesting plans (workflows).  ...  They open up the available meta-data to help users make informed decisions. a The boxes stand consecutively for the Data Selection, Preprocessing+transformation, Data Mining, and Postprocessing step. b  ...  Despite many proposed ontologies, there is of yet no consensus on an ontology for DM or KD, but we hope that such an ontology will arise over the coming years.  ... 
doi:10.1007/978-3-642-20980-2_4 fatcat:h7qh6p2cbfdophxgurm6tbio3e

A Research Agenda for IOT Adaptive Architectures

Jairo Ariza, Camilo Mendoza, Kelly Garcés, Nicolás Cardozo
2018 Proceedings (MDPI)  
Changes may come from different elements of the architecture underlying an IOT system.  ...  As a starting point, we design an architecture to deal with the posited challenges.  ...  From this we learned that our architecture has to be flexible enough to allow developers to plug, compare and tune new matching heuristics.  ... 
doi:10.3390/proceedings2191229 fatcat:g7hpgyke7fdgxj3bboi25sslnm

Creating and visualizing fuzzy document classification

Judith Gelernter, Dong Cao, Raymond Lu, Eugene Fink, Jaime G. Carbonell
2009 2009 IEEE International Conference on Systems, Man and Cybernetics  
An advantage of our interface is that it allows users to visualize those differences quickly.  ...  The novelty of our work is in integrating fuzzy classification algorithms with an interface to visualize fuzzy results.  ...  ACKNOWLEDGMENTS We are grateful for the advice of Michael Lesk from Rutgers University for all his help along the way.  ... 
doi:10.1109/icsmc.2009.5346682 dblp:conf/smc/GelernterCLFC09 fatcat:6y26gb3vrvf6lifaho6oi22mcm

Automatic Typing of DBpedia Entities [chapter]

Aldo Gangemi, Andrea Giovanni Nuzzolese, Valentina Presutti, Francesco Draicchio, Alberto Musetti, Paolo Ciancarini
2012 Lecture Notes in Computer Science  
We present Tìpalo, an algorithm and tool for automatically typing DBpedia entities.  ...  Types are identified by means of a set of heuristics based on graph patterns, disambiguated to WordNet, and aligned to two top-level ontologies: Word-Net supersenses and a subset of DOLCE+DnS Ultra Lite  ...  Conclusions and Future Work We have presented Tìpalo, an implemented method that formalizes entity definitions extracted from Wikipedia for automatically typing DBpedia entities and linking them to other  ... 
doi:10.1007/978-3-642-35176-1_5 fatcat:t3wvn5mijnedhi6jbnohhop63e

Semantic enrichment for improving systems interoperability

Xiaomeng Su, Sari Hakkarainen, Terje Brasethvik
2004 Proceedings of the 2004 ACM symposium on Applied computing - SAC '04  
Based on the similarities measure, a heuristic method is used to establish mapping assertions for the two ontologies. The method is illustrated using a product catalogue scenario.  ...  similarities between concepts in two ontologies.  ...  It is generally understood that UNSPSC classifies products from a suppliers perspective, while Eclass is from a users perspective.  ... 
doi:10.1145/967900.968227 dblp:conf/sac/SuHB04 fatcat:fmhkkxszzzd5llimdq7onlzhcu
« Previous Showing results 1 — 15 out of 3,392 results